Application of Deep Learning for Preoperative prostate MRI segmentation in Postoperative Inguinal Hernia Prediction after robot-assisted radical prostatectomy

Application of Deep Learning for Preoperative prostate MRI segmentation in Postoperative Inguinal Hernia Prediction after robot-assisted radical prostatectomy | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Application of Deep Learning for Preoperative prostate MRI segmentation in Postoperative Inguinal Hernia Prediction after robot-assisted radical prostatectomy Jiawei Zhang, Xuesheng Fan, Weiwei Sheng, Maoming Xiong, Lisheng Wu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9224900/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Purpose Postoperative inguinal hernia (PIH) is a common complication after radical prostatectomy and has attracted significant attention from surgeons due to the need for additional surgical treatment. This study aimed to identify risk factors for PIH after robot-assisted radical prostatectomy (RARP) and determine if MRI can be used as a potential predictor of PIH. Methods A retrospective case-control study was conducted to analyze the clinical data, preoperative prostate MRI images, and postoperative pathological reports of 540 patients who underwent RARP from January 2020 to December 2024. A deep segmentation network is employed to process preoperative prostate MRI images and extract prostate MRI parameters automatically. Logistic regression analysis is performed to identify independent risk MRI factors of PIH, and Kaplan-Meier analysis was used to investigate the survival curve without PIH after RARP. Results The median follow-up time was 15.3 ± 6.6 months, and a total of 61 (11.3%) patients developed PIH. There were significant differences in Sag-H and Sag-W measured on sagittal T2-weighted images ( p < 0.05 ). The MRI-based prostate volume (MRI-PV) (62.250 ± 27.264 vs 53.980 ± 23.702) (ml) showed a significant statistical difference between the two groups ( p = 0.012 ). In the univariate and multivariate logistic regression analysis, the postoperative pathological T stage (≥ T3) was a significant risk factor for the occurrence of PIH ( p = 0.011 ). Sag-H (> 5.095cm), Sag-W (> 4.301cm), and MRI-PV (> 67.490ml) were risk factors for PIH after RARP ( p < 0.05 ). There was a high correlation between MRI-PV and pathology-based prostate volume (PA-PV) in the PIH group (r = 0.923, p 5.095cm ), Sag-W ( > 4.301cm ), and MRI-PV ( > 67.490ml ) might be related to the occurrence of PIH. These indicators show significant promise in helping us take measures to prevent PIH occurrence. Deep Learning Inguinal Hernia Robot-assisted radical prostatectomy Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Introduction Prostate cancer (PC) is one of the most common cancers among men in the world [ 1 ]. Radical prostatectomy (RP) has been considered as the gold-standard treatment for PC. Over time, surgical techniques for RP have evolved from open surgery to laparoscopy, and now to robot-assisted laparoscopic radical prostatectomy (RARP). RARP has recently gained widespread popularity over open or traditional laparoscopic surgery worldwide, with a significant increase in the number of cases. This widely used application is attributed to the inherent advantages of a minimally invasive approach and the enhanced dexterity it offers in the confined pelvic space. Although it is acknowledged that RP surgical techniques are effective and safe, several postoperative complications can occur, such as urinary incontinence and erectile dysfunction [ 2 ]. In recent years, PIH has attracted increasing attention from surgeons as a major complication, mainly because it is a common disease in the aging male population [ 3 ]. Previous research has shown that the incidence of PIH after open retropubic radical prostatectomy (ORP) ranges from 10% to 24% in the first several postoperative years after surgery, in contrast, the occurrence rates of PIH are lower after laparoscopic radical prostatectomy (LRP), ranging from 5.3% to 14.0% [ 4 ]. Additionally, previous studies had reported that the incidence of PIH is higher in patients who undergo RARP compared to those who do not [ 5 – 6 ]. However, these studies had not provided specific incidences or identified the risk factors for PIH after RARP. Furthermore , patients with PIH typically require surgical treatment with additional mesh, which increases the duration of operation and the risk of anesthesia [ 7 ]. This significantly affects the patient's quality of life and increases the financial burden on medical insurance. Therefore, how to predict the occurrence of PIH so as to take preventive measures have significant clinical significance. Magnetic resonance imaging (MRI) is one of the most important medical imaging techniques for the diagnosis and therapeutic effect detection of PC [ 8 – 9 ]. The Prostate Imaging Reporting and Data System (PIRADS) provides a standardized framework for reporting and evaluating prostate MRI [ 10 ]. However, applying this system requires experienced radiologists and is time-consuming. Some studies have developed scoring systems based on PIRADS to predict whether patients with PC need surgical treatment [ 11 ]. Multiparametric MRI scans have also been shown to improve surgical decision-making for nerve-sparing versus non–nerve-sparing approaches, thereby helping to prevent postoperative complications such as urinary incontinence and erectile dysfunction after RP [ 12 ]. In addition, several studies have predicted patient survival using prostate MRI parameters in combination with pathological results [ 13 ]. Nevertheless, few studies have investigated the prediction of PIH by fully exploiting the potential of preoperative MRI parameters. Recently, deep learning (DL) techniques have emerged as a promising tool for various medical applications, including image segmentation and medical image feature extraction [ 14 – 15 ]. Previous studies have demonstrated that MRI-based DL models can effectively assess PC risk and predict clinical outcomes by integrating imaging features and clinical factors [ 16 – 17 ]. However, the application of MRI-based DL models in predicting PIH based on preoperative prostate MRI remained underexplored. This study aimed to investigate the potential of the MRI-based DL models for the prediction of PIH following RARP and identify specific risk MRI factors. This can ultimately assist surgeons in implementing appropriate preventive measures during RP. Materials and methods Data preparation This study was approved by the Ethics Committee of the First Affiliated Hospital of Anhui Medical University (No. PJ2024-11-62), Hefei, China. We retrospectively analyzed 540 consecutive patients who underwent RARP at First Affiliated Hospital of Anhui Medical University in eastern China between January 2020 and December 2024. All patients underwent MRI examinations within one month before the operation, and written informed consents were provided by all patients. This study was performed following the Declaration of Helsinki. Exclusion criteria of patients: (1) Conservative treatment or endocrine therapy for advanced metastatic prostate cancer. (2) All patients who have previously undergone surgical treatment for inguinal hernia (IH) or currently have concurrent IH. (3) Preoperative radiotherapy and chemotherapy or previous urethral prostatectomy. (4) Severe preoperative pulmonary function abnormalities. (5) Patients with cirrhotic ascites and uremia undergoing peritoneal dialysis. (6) The case imaging data are incomplete. (7) Follow-up loss of contact. To detect subclinical preoperative IH as much as possible and increase the reliability of this study, we retrospectively examined preoperative MRI scans for transverse fascial weakness and reviewed all intraoperative videos during RARP to check whether there was a combined status of subclinical IH. Finally, a total of 540 patients were included in this study. The clinical baseline data of the patients are listed in Table 2 . Surgical procedures and medical follow-up protocol All RARPs were performed with a DaVinci Robot Surgical System (Intuitive Surgical G.K., USA). Standard techniques of the operative procedures were performed with a trans-peritoneal approach. The space of Retzius was dissected. Obturator lymph node dissection was performed for patients with moderate risk, and extended lymph node dissection was positively performed in high risk patients. Neurovascular bundle preservation was strictly attempted in patients without the presence of cancer at the peripheral margin in order to preserve the patients' sexual function. The procedures were performed by experienced surgical team with an annual surgical volume of over 50 RARP cases. Postoperative follow-up were conducted at 1, 3, 6, 9 ,and 12months in the first year, then every 6 months as a routine procedure. PIH was diagnosed based on clinical symptoms, a physical examination and results of ultrasound examination in the inguinal area. The Development of Deep Learning for Preoperative prostate MRI segmentation and prostate MRI parameter extraction MRI examinations were conducted using a 3.0T MRI system (Discovery 750, GE Healthcare). The MRI scan sequences included axial, coronal, and sagittal propeller FR FSE T2WI covering the prostate apex to base and seminal vesicles. The maximum longitudinal length (Ax-H) and the maximum transverse length of the prostate (Ax-W), was measured on axial T2-weighted images (Fig. 1 a) and the maximum longitudinal (Sag-H) and maximum lateral length (Sag-W) were measured on mid-sagittal T2-weighted images (Fig. 1 b). All patients’ MRI-PV was calculated by the ellipsoid formula (Volume = Sag-H * Sag-W * Ax-W * π/6). We implement a deep segmentation network U-Net architecture for preoperative prostate MRI segmentation by using Python and PyTorch. The AX mode dataset was collected to train U-Net consists of 1,181 images from 197 patients, with 29 patients having PIH and 168 healthy controls (HC). The dataset is split at the participant level into a training set and a testing set with a ratio of 8:2, as offered in Table 1 . The experiments are run on an NVIDIA TITAN V GPU, and the Adam optimizer with default parameter settings is utilized to optimize the U-Net. The training epochs, batch size, and initial learning rate are set to 100, 8, and 0.00015. The Cosine Annealing LR scheduler is applied to adjust the learning rate. MRI images are resized to 256×256 as the inputs for the U-Net (Fig. 2 ). The deep segmentation network achieved an accuracy of 98.95% in correctly segmenting the prostate MRI images. The prostate MRI image segmentation results are then used to extract preoperative prostate MRI parameters. To ensure precision, the segmented MRI images are checked twice, and any MRI images with segmentation errors are manually corrected. Table 1 Preoperative prostate MRI segmentation dataset distribution Variables Training Test Total Images Participants Images Participants Images Participants AX No-PIH 779 130 228 38 1007 168 PIH 162 27 12 2 174 29 SAG No-PIH 804 134 198 33 1002 167 PIH 132 22 42 7 174 29 Statistical analysis Continuous variables were described as mean and standard deviation. An independent t- test or Mann-Whitney U test was used to investigate the significant difference of continuous variables between two groups. Categorical variables were described as numbers and percentages. The χ2 test /Fisher's exact test was used to compare categorical variables. A two-tailed value of p < 0.05 was considered statistically significant. Univariate and multivariate logistic regression analyses were employed to identify the risk factors of PIH, and the odds ratio (OR) and 95% confidence interval (CI) were calculated. Pearson correlation analysis was used to construct correlation coefficients between MRI-PV and PA-PV. Linear regression analysis was used to calculate the variability in the MRI-PV and PA-PV. The Bland-Altman plot was applied to show the relationship between MRI-PV and PA-PV. All statistical analysis is conducted using IBM SPSS (version 26.0; IBM Corporation, Armonk, New York, USA). All graphs were created by using GraphPad Prism software version 9.5 (GraphPad Software, La Jolla, CA, USA). Results Demographics and clinical characteristics of patients A total of 540 patients who underwent RARP were included in this study. The demographics and clinical characteristics of patients are summarized in Table 2 . All operations were performed via transperitoneal or retropubic approach by using the Da Vinci surgical robot system. The average operation time was 196.4 ± 46.5 mins, and the median follow-up time was 15.3 ± 6.6 months. Among them, 61 cases (11.3%) with PIH were treated as the PIH group. The remaining 479 cases (88.7%) were taken as the control group. Among the PIH group, there were 60 cases of indirect hernia, and there was 1 case of direct hernia. The demographics and clinical characteristics of all patients were shown in Table 2 . There were no statistically significant differences between the two groups in terms of age, BMI index, smoking history, drinking history, diabetes, preoperative PSA level, operation time, Gleason score, intraoperative pelvic lymph node dissection (PLND), and pathological N stage. The T stage of postoperative pathology and PA-PV showed significant differences between the two groups of patients ( p < 0.05 , Table 2 ). The PIH-free survival rates at 1 and 2 years after RARP were 91.11% and 89.26%, respectively. The average onset time of PIH was (7.8 ± 5.8) months after operation. The PIH-free rate at 1, 2, and 3 years postoperatively was 85.9%, 79.6%, and 79.6% among patients with TMN(≥ T3), and 91.6%, 89.5%, and 88.2% among patients with TMN(≤ T2) ( p = 0.017 , Fig. 3 a). Table 2 Demographics and clinical characteristics of patients Baselinel characteristics Overall(540) Postoperative inguinal hernia χ²/t p-value Yes(n = 61) No(n = 479) Age(years) 0.296 0.586 <65 121(22.4%) 12(19.7%) 109(22.8%) ≥ 65 419(77.6%) 49(80.3%) 370(77.2%) BMI(kg/m²) 3.086 0.214 25 167(31.0%) 13(21.3%) 154(32.2%) Somking history 0.009 0.924 yes 55(10.2%) 6(9.8%) 49(10.2%) no 485(89.8%) 55(90.2%) 430(89.8%) Drinking history 0.399 0.528 yes 47(8.7%) 4(6.6%) 43(9.0%) no 493(91.3%) 57(93.4%) 436(91.0%) DM 0.358 0.550 Yes 85(15.7%) 8(13.1%) 77(16.1%) No 455(84.3%) 53(86.9%) 402(83.9%) preoperative PSA(ng/ml) 2.039 0.361 20 191(35.4%) 17(27.9%) 174(36.3%) preoperative Gleason grade 4.711 0.095 ≤ 6 101(18.7%) 12(19.7%) 89(18.6%) 7 250(46.3%) 35(57.4%) 215(44.9%) ≥ 8 189(35.0%) 14(22.9%) 175(36.5%) PLND 0.068 0.794 yes 213(39.4%) 25(41.0%) 188(39.2%) no 327(60.6%) 36(59.0%) 291(60.8%) Operation duration(mins) 1.074 0.300 <180 285(52.8%) 36(59.0%) 249(52.0%) ≥ 180 255(47.2%) 25(41.0%) 230(48.0%) Pathological T stage 6.674 0.010 T1-T2 416 (77.0%) 39 (63.9%) 377 (78.7%) ≥T3 124(23.3%) 22 (36.1%) 102 (21.3%) Pathological N stage 0.670 0.413 N0 489(90.6%) 57(93.4%) 432(90.2%) N+ 51(9.4%) 4(6.6%) 47(9.8%) PA-PV(ml) 5.92 0.015 <63.61 405(75%) 38(62.3%) 367(76.6%) ≥ 63.61 135(25%) 23(37.7%) 112(23.4%) BMI body mass index, DM diabetes, PSA prostate-specific antigen, PLND Pelvic lymph node dissection, PV prostate volume MRI-based prostate parameters and MRI-PV All MRI prostate parameters and MRI-PV statistics of the two groups were presented in Table 3 . The Sag-H measured on the sagittal T2-weighted image was 5.065 ± 0.891(cm) in the PIH group and 4.725 ± 0.787(cm) in the non-PIH group. It was observed that there was a significant difference between the two groups ( p = 0.002 , Table 3 ); the Sag-W was 4.360 ± 0.693(cm) in the PIH group and 4.174 ± 0.672(cm) in the non-PIH group ( p = 0.043 , Table 3 ). However, there were no significant differences in Ax-H (4.228 ± 0.747 vs 4.250 ± 0.643) (cm) and Ax-W (5.088 ± 0.819 vs 4.994 ± 0.750) (cm) on the axial T2-weighted images ( p > 0.05 , Table 3 ). The MRI-PV (62.250 ± 27.264 vs 53.980 ± 23.702) (ml), showing a significant difference between the two groups ( p = 0.012 , Table 3 ). Table 3 MRI variables and prostate volume based MRI Variables PIH Statistic p Yes No Ax-H (cm) 4.248 ± 0.655 4.228 ± 0.747 4.250 ± 0.643 t = 0.250 0.802 Ax-W (cm) 5.005 ± 0.758 5.088 ± 0.819 4.994 ± 0.750 t = 0.915 0.361 Sag-H (cm) 4.763 ± 0.806 5.065 ± 0.891 4.725 ± 0.787 t = 3.736 0.002 Sag-W (cm) 4.195 ± 0.676 4.360 ± 0.693 4.174 ± 0.672 t = 2.026 0.043 MRI-PV(ml) 54.914 ± 24.245 62.250. ± 27.264 53.980 ± 23.702 t = 2.522 0.012 Univariable and multivariable Logistic regression analyses for predictive factors of PIH In the univariate Logistic regression analysis, the postoperative pathological T stage (≥ T3) was a risk factor for PIH after RARP ( p = 0.011 , Table 4 ). The OR was 2.106(95%CI:1.192–3.720). Compared with other MRI prostate parameters, such as Sag-H (> 5.095cm), Sag-W (> 4.301cm), and MRI-PV (> 67.490ml) were risk factors for PIH after RARP ( p < 0.05 , Table 4 ). The OR values were 1.909 (95%CI:1.087–3.356), 1.784 (95%CI:1.041–3.057) ,and 2.463 (95%CI:1.421–4.269). In the multivariate Logistic regression analysis, the postoperative pathological T stage (≥ T3) and MRI-PV (> 67.490ml) were risk factors for the occurrence of PIH ( p < 0.05 , Table 4 ), and the adjusted OR values were 3.583 (95%CI:0.972–13.210) and 1.772 (95%CI:1.036–3.031). The PIH-free rate at 1, 2, and 3 years postoperatively was 85.5%, 79.8%, and 76.9% among patients with Sag-H (> 5.095cm), and 92.9%, 91.1%, and 91.1% among patients with Sag-H (≤ 5.095cm) ( p 4.301cm) and 90.5% with Sag-W (≤ 4.301cm) ( p = 0.011 , Fig. 3 c). The PIH-free rate at 2years postoperatively was 78.1% with MRI-PV (> 67.490ml) and 90.2% with MRI-PV (≤ 67.490ml) ( p = 0.001 , Fig. 3 d). Table 4 Univariate and multivariate analyses for the risk factors for PIH in patients with RARP Variables Univariate analysis Multivariate analysis OR HR(95% CI) p value OR HR(95% CI) p value Age(<65vs ≥ 65) 1.203 0.618–2.342 0.587 1.490 BMI(kg/m²) 0.644 0.390–1.065 0.086 0.293 Somking history 0.957 0.392–2.338 0.924 1.093 Drinking history 0.712 0.246–2.056 0.530 0.548 DM 0.788 0.360–1.723 0.551 2.217 preoperative PSA(ng/ml) 0.809 0.576–1.137 0.222 0.914 preoperative Gleason grade 0.750 0.510–1.104 0.145 0.811 PLND 1.068 0.621–1.836 0.813 2.054 Opreation duration (<180min vs ≥ 180min) 0.752 0.438–1.291 0.301 0.348 Pathological T stage (≤T2vs.≥T3) 2.106 1.192–3.720 0.011 3.583 0.972–13.210 0.045 Pathological N stage(N0 vs.N+) 0.776 0.297–2.030 0.606 Ax-H(cm) 1.109 0.651–1.890 0.703 Ax-W(cm) 1.286 0.752–2.198 0.358 Sag-H(cm) 1.909 1.087–3.356 0.025 2.021 0.934 ~ 4.373 0.074 Sag-W(cm) 1.784 1.041–3.057 0.035 2.796 0.245–31.941 0.408 MRI-PV(ml) 2.463 1.421 ~ 4.269 0.001 3.776 1.136–13.031 0.037 Comparison between MRI-PV and PA-PV There was a high degree of correlation between MRI-PV and PA-PV in non-PIH group (r = 0.870, p < 0.01 , Fig. 4 a), the same trend could also be observed in PIH group (r = 0.923, p < 0.05 , Fig. 4 b). MRI-PV overestimated PA-PV by 1.8ml in non-PIH group (Fig. 5 a), and 4.4ml in PIH group (Fig. 5 b). Linear regression analysis showed that the difference between MRI-PV and PA-PV was negatively related to PV (r= -0.415, p < 0.01 , Fig. 4 c ) . If PA-PV was 63.25ml, MRI-PV underestimated PA-PV (Fig. 4 c). The Bland-Altman plots depict the relationship of the difference between MRI-PV and PA-PV, were shown in Fig. 5 . The MAPE of MRI-PV was 18.93% in the non-PIH group (Fig. 5 a), 18.66% in the PIH group (Fig. 5 b). For the entire cohort, the number of people with percentage error within ±l0% and ± 20% were 194/540 (35.9%), and 396/540 (73.3%), respectively. Discussion This study offered a unique means to measure PV for the occurrence of PIH prediction after RARP by using MRI-based DL models. Although RARP has improved the prognosis of urinary incontinence and erectile dysfunction compared to ORP, its impact on the incidence of PIH still remains controversial [ 18 ]. The incidence of PIH after LRP has been previously reported to be lower than that after ORP [ 19 ]. In recent years, with the wide use of surgical robots, the incidence of PIH after RARP has gradually become a hot research topic. Anatomical Retzius-space preservation is associated with a lower incidence of PIH development after RARP. Some studies have reported that the incidence of PIH after RARP ranges from 5.8% (18/577) to 10.8% (78/720) [ 20 – 21 ]. Our study retrospectively analyzed the clinical data, preoperative prostate MRI images ,and postoperative pathological reports of 540 patients admitted to our hospital and found that the overall incidence of inguinal hernia was 11.3% (61/540), which is close to the findings of most current studies. We also found that the average time of occurrence for PIH was 15.3 ± 6.6 months, which has certain guiding significance for postoperative follow-up. In addition, few studies focused on the risk factors and preventive measures for PIH after RARP. Liu L et al. found that patients who underwent retropubic radical prostatectomy were associated with an increased incidence of PIH, especially those over 80 years old [ 22 ]. Previous study from China showed that there was no statistically significant difference in age between the PIH group and No-PIH group of patients [ 23 ]. In some regional studies, low BMI has been identified as a risk factor for PIH, with a dangerous threshold of BMI yet to be determined, approximately at BMI < 25 kg/m² [ 24 ]. However, several studies have found that low BMI does not increase the occurrence risk of PIH [ 25 ]. In the past years, bladder outlet obstruction (BOO) caused by post-RP anastomotic stricture, which leads to to PIH [ 26 ], and Pelvic lymph node dissection(PLND) during RP can cause postoperative adhesion contraction of pelvic muscles, resulting in increased abdominal pressure in the inner ring orifice area and an increased incidence of PIH [ 27 ]. After the popularization of robotic surgery, suturing, dissociation ,and PLND in narrow spaces were no longer difficult, and these factors might become insignificant. This study found that Age, BMI, PLND, hypertension, diabetes, PSA level, and operation duration were not statistically significant to occurrence of inguinal hernia after prostate cancer surgery ( p > 0.05 ). The specific mechanism of PIH after radical prostatectomy is not yet clear. However, most methods predicted the occurrence of PIH that required intraoperative conditions and postoperative pathology, thereby limiting their application before the operation. How to use preoperative clinical data and imaging examinations to predict the occurrence of PIH and actively take preventive measures is noteworthy. Imaging examinations play a crucial role in the screening, diagnosis, and prognosis of PC. Some studies have utilized CT to observe indicators such as the psoas major muscle and rectus abdominis muscle to analyze the occurrence of PIH [ 28 ]. These results suggested that the development of PIH is related to the strength and volume of abdominal wall muscles. However, due to the limitation of soft tissue visualization, CT was not as accurate as MRI in the detailed diagnosis and prognosis evaluation of PC. In the clinical process, MRI played a significant role in the treatment of PC. Previous studies have used preoperative MRI to assist in the diagnosis [ 29 ], decision-making [ 30 ] and predict postoperative survival of PC [ 31 ] by observing various characteristics of the prostate, such as shape, size, and signal intensity. Among the various MRI prostate parameters, PV has been proven to be important for PC screening and prognosis evaluation [ 32 ]. Previous clinical studies have confirmed that PA-PV is a significant indicator to help surgeons select the most appropriate treatment, reduce overtreatment of clinically insignificant PC, and predict lymph node invasion, biochemical recurrence, and clinical recurrence [ 33 ]. In the daily work of active surveillance, PA-PV was divided by the number of biopsies to obtain the volume/biopsy ratio could determine the best predictors for positive biopsies [ 34 ]. Additionally, a larger prostate has a significant negative impact on to the PIH-free of post-prostatectomy incontinence despite undergoing the same RARP [ 35 ]. However, few studies have investigated the relationship between MRI-PV and PIH. Previous research had found that due to the need for bladder-urethral anastomosis during prostatectomy, a comparison of preoperative and postoperative sagittal MRI images revealed a downward shift of the rectovesical (RE) pouch by approximately 2 to 3cm [ 36 ]. Therefore, we hypothesized that this downward shift of the RE pouch causes traction on the extraperitoneal tissues and vas deferens following urethral anastomosis, which in turn pulls the internal ring inward, alters pressure distribution within the myopectineal orifice, and contributes to the development of PIH. The factor influences the degree of RE downward shift is the prostate volume; the more severe the diseased prostate, the more pronounced the downward shift after resection, thus increasing the incidence of PIH. However, most of the experimental measurements of PA-PV were performed in vitro after surgery, which had certain limitations. Firstly, formalin fixation leads to tissue dehydration, which reduces the actual volume in vivo. Secondly, because PA-PV is measured postoperatively, preventive measures cannot be taken in time during the surgical operation. Historically, Planimetry-based assessment of PV was considered to be the closest to in vivo prostate size [ 37 ]. However, this method was time-consuming, cumbersome, required special software. Therefore, it was not widely used in daily clinical practice. Although less accurate than the Planimetry method, MRI-PV calculation using the ellipsoid formula has been widely used due to its effectiveness, accuracy, and radiation-free nature. Meanwhile, preoperative standardized assessment based on PI-RADS v2.1 was performed by experienced radiologists or trained specialists; this process is neither time-saving nor cost effective [ 38 ]. In recent years, artificial intelligence has been increasingly applied to radiology, and relevant studies have confirmed the feasibility and effectiveness of automatic MRI segmentation based on deep learning algorithms [ 39 ]. However, the application of these deep learning models is largely limited to academic research rather than clinical applications. In this study, we utilized a deep learning-based automatic segmentation algorithm to measure preoperative prostate MRI parameters across different axes, estimate prostate volume using the ellipsoid formula, and evaluate its potential for predicting PIH occurrence. This method may enable early identification of high-risk patients undergoing RARP and facilitate timely preventive measures. However, the present study has certain limitations, and prospective multicenter trials are needed to further validate the predictive value of this method for PIH. Conclusion The method using the automatic segmentation of a deep learning algorithm based on preoperative prostate MRI could measure the parameters of the prostate in different axes accurately. Larger specimen volume and higher T-stage maybe potential risk factors for the occurrence of PIH. Compared with traditional methods, this method has clinical significance due to its characteristics of lower cost and higher accuracy. Abbreviations index Ax-H the maximum longitudinal length measured on axial T2-weighted images Ax-W the maximum transverse length measured on axial T2-weighted images CI confidence interval DL deep learning HC healthy controls LRP laparoscopic radical prostatectomy MRI magnetic resonance imaging OR the odds ratio ORP open retropubic radical prostatectomy PC prostate cancer PLND pelvic lymph node dissection PIH postoperative inguinal hernia PIRADS prostate Imaging Reporting and Data System PV prostate volume RARP robot-assisted radical prostatectomy RP radical prostatectomy Sag-H the maximum longitudinal length measured on mid-sagittal T2-weighted images Sag-W the maximum lateral length measured on mid-sagittal T2-weighted images Declarations Ethical approval and consent to participate Written informed consents were obtained by all patients before enrollment. This study was performed following the Declaration of Helsinki. Ethical approval was obtained from the Ethics Committee of the First Affiliated Hospital of Anhui Medical University (No. PJ2024-11-62), Hefei, China. Consent for publication Not applicable. Competing interests The authors declare that they have no competing interests. Funding This study was supported by the National Natural Science Foundation of China (Grant No. 82573191), Open Fund of Key Laboratory of Anti-inflammatory and Immune Medicine (Grant No.KFJJ-2023-10), Ministry of Education, P.R. China (Anhui Medical University), Higher education quality project of Anhui Province (Grant No. 2023jyxm1095) and Scientific Research Foundation of Education Department of Anhui Province of China (Grant No. 2025AHGXZK30334). Author Contribution The study was conceived and designed by Jiawei Zhang, Xiaoqing Zhang, and Guodong Cao. Data were obtained by Xuesheng Fan and Weiwei Sheng. Data analysis and interpretation were performed by Xiaoqing Zhang and Jiawei Zhang. The manuscript was drafted by Jiawei Zhang, and revised by Xiaoqing Zhang, Maoming Xiong, Lisheng Wu, and Guodong Cao. All authors have read and commented on the working versions and approved the final manuscript before submission. Acknowledgements We would like to express our gratitude to Zunjie Xiao from the Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, for his assistance with the statistical analysis in this study. Data Availability The datasets used during the current study are available from the corresponding author on reasonable request. References Han B, Zheng R, Zeng H, Wang S, Sun K, Chen R, Li L, Wei W, He J. Cancer incidence and mortality in China, 2022. J Natl Cancer Cent. 2024;4(1):47–53. https://doi.org/10.1016/j.jncc.2024.01.006 . Hamdy FC, Donovan JL, Lane JA, Metcalfe C, Davis M, Turner EL, Martin RM, Young GJ, Walsh EI, Bryant RJ, Bollina P, Doble A, Doherty A, Gillatt D, Gnanapragasam V, Hughes O, Kockelbergh R, Kynaston H, Paul A, Paez E, Powell P, Rosario DJ, Rowe E, Mason M, Catto JWF, Peters TJ, Oxley J, Williams NJ, Staffurth J, Neal DE. Fifteen-Year Outcomes after Monitoring, Surgery, or Radiotherapy for Prostate Cancer. N Engl J Med. 2023;388(17):1547–58. https://doi.org/10.1056/NEJMoa2214122 . Yatabe Y, Tanioka T, Waseda Y, Yamaguchi K, Ogo T, Fujiwara H, Okuno K, Kawada K, Haruki S, Tokunaga M, Fujii Y, Kinugasa Y. Inguinal hernia repair in patients with artificial urinary sphincter after radical prostatectomy. Hernia. 2024;28(4):1331–6. https://doi.org/10.1007/s10029-024-03040-w . Aiolfi A, Bona D, Calì M, Manara M, Bonitta G, Cavalli M, Bruni PG, Carmignani L, Danelli P, Bonavina L, Köckerling F, Campanelli G. Is previous radical prostatectomy a contraindication to minimally invasive inguinal hernia repair? A contemporary meta-analysis. Hernia. 2024;28(5):1525–36. https://doi.org/10.1007/s10029-024-03098-6 . Nilsson H, Stranne J, Hugosson J, Wessman C, Steineck G, Bjartell A, Carlsson S, Thorsteinsdottir T, Tyritzis SI, Lantz A, Wiklund P, Haglind E. Risk of hernia formation after radical prostatectomy: a comparison between open and robot-assisted laparoscopic radical prostatectomy within the prospectively controlled LAPPRO trial. Hernia. 2020;26(1):157–64. https://doi.org/10.1007/s10029-020-02178-7 . Toide M, Ebara S, Tatenuma T, Ikehata Y, Nakayama A, Kawase M, Sasaki T, Yoneda T, Sakaguchi K, Teishima J, Makiyama K, Kitamura H, Saito K, Koie T, Inoue T, Urakami S, Koga F. Incidence and risk factors of inguinal hernia after robot-assisted radical prostatectomy: a retrospective multicenter cohort study in Japan (the MSUG94 group). J Robotic Surg. 2024;18(1):38. https://doi.org/10.1007/s11701-023-01761-1 . Funamizu N, Mineta SHO, Ozaki T, Mishima K, Igarashi K, Omura K, Takada Y, Wakabayashi GO. (2022) Utility of Robot-assisted Laparoscopic Transabdominal Preperitoneal Repair of Inguinal Hernia Following Robot-assisted Laparoscopic Radical Prostatectomy. In Vivo 36(3):1432–1437. https://doi.org/10.21873/invivo.12848 Giganti F, Dickinson L, Orczyk C, Haider A, Freeman A, Emberton M, Allen C, Moore CM. Prostate Imaging after Focal Ablation (PI-FAB): A Proposal for a Scoring System for Multiparametric MRI of the Prostate After Focal Therapy. Eur Urol Oncol. 2023;6(6):629–34. https://doi.org/10.1016/j.euo.2023.04.007 . Berlin A, Brierley J, Cornford P, Chung P, Giannopoulos E, Mason M, Mottet N, Gospodarowicz M. TNM Staging of Prostate Cancer: Challenges in Securing a Globally Applicable Classification. Eur Urol. 2022;82(2):e52–53. https://doi.org/10.1016/j.eururo.2022.04.019 . Turkbey B, Rosenkrantz AB, Haider MA, Padhani AR, Villeirs G, Macura KJ, Tempany CM, Choyke PL, Cornud F, Margolis DJ, Thoeny HC, Verma S, Barentsz J, Weinreb JC. Eur Urol. 2019;76(3):340–51. https://doi.org/10.1016/j.eururo.2019.02.033 . Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2. Peters M, Eldred-Evans D, Kurver P, Falagario UG, Connor MJ, Shah TT, Verhoeff JJC, Taimen P, Aronen HJ, Knaapila J, Montoya Perez I, Ettala O, Stabile A, Gandaglia G, Fossati N, Martini A, Cucchiara V, Briganti A, Lantz A, Picker W, Haug ES, Nordström T, Tanaka MB, Reddy D, Bass E, van Rossum PSN, Wong K, Tam H, Winkler M, Gordon S, Qazi H, Boström PJ, Jambor I, Ahmed HU. Predicting the Need for Biopsy to Detect Clinically Significant Prostate Cancer in Patients with a Magnetic Resonance Imaging–detected Prostate Imaging Reporting and Data System/Likert ≥ 3 Lesion: Development and Multinational External Validation of the Imperial Rapid Access to Prostate Imaging and Diagnosis Risk Score. Eur Urol. 2022;82(5):559–68. https://doi.org/10.1016/j.eururo.2022.07.022 . Bahler CD, Tachibana I, Tann M, Collins K, Swensson JK, Green MA, Mathias CJ, Tong Y, Yong C, Boris RS, Brocken E, Hutchins GD, Sims JB, Hill DV, Smith N, Ferari C, Love H, Koch MO. Comparing Magnetic Resonance Imaging and Prostate-Specific Membrane Antigen–Positron Emission Tomography for Prediction of Extraprostatic Extension of Prostate Cancer and Surgical Guidance: A Prospective Nonrandomized Clinical Trial. J Urol. 2024;212(2):290–8. https://doi.org/10.1097/ju.0000000000004032 . Lee HW, Kim E, Na I, Kim CK, Seo SI, Park H. Novel Multiparametric Magnetic Resonance Imaging-Based Deep Learning and Clinical Parameter Integration for the Prediction of Long-Term Biochemical Recurrence-Free Survival in Prostate Cancer after Radical Prostatectomy. Cancers. 2023;15(13):3416. https://doi.org/10.3390/cancers15133416 . Jiang Y, Zhou K, Sun Z, Wang H, Xie J, Zhang T, Sang S, Islam MT, Wang J-Y, Chen C, Yuan Q, Xi S, Li T, Xu Y, Xiong W, Wang W, Li G, Li R. Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics. Cell Rep Med. 2023;4(8):101146. https://doi.org/10.1016/j.xcrm.2023.101146 . Beuque MPL, Lobbes MBI, van Wijk Y, Widaatalla Y, Primakov S, Majer M, Balleyguier C, Woodruff HC, Lambin P. Combining Deep Learning and Handcrafted Radiomics for Classification of Suspicious Lesions on Contrast-enhanced Mammograms. Radiology. 2023;307(5):e221843. https://doi.org/10.1148/radiol.221843 . Schrader A, Netzer N, Hielscher T, Görtz M, Zhang KS, Schütz V, Stenzinger A, Hohenfellner M, Schlemmer H-P, Bonekamp D. Prostate cancer risk assessment and avoidance of prostate biopsies using fully automatic deep learning in prostate MRI: comparison to PI-RADS and integration with clinical data in nomograms. Eur Radiol. 2024;34(12):7909–20. https://doi.org/10.1007/s00330-024-10818-0 . Ponsiglione A, Gambardella M, Stanzione A, Green R, Cantoni V, Nappi C, Crocetto F, Cuocolo R, Cuocolo A, Imbriaco M. Radiomics for the identification of extraprostatic extension with prostate MRI: a systematic review and meta-analysis. Eur Radiol. 2023;34(6):3981–91. https://doi.org/10.1007/s00330-023-10427-3 . Ambrosini F, Knipper S, Tilki D, Heinzer H, Salomon G, Michl U, Steuber T, Pose RM, Budäus L, Maurer T, Terrone C, Tennstedt P, Graefen M, Haese A. Robot-assisted vs open retropubic radical prostatectomy: a propensity score-matched comparative analysis based on 15 years and 18,805 patients. World J Urol. 2024;42(1):131. https://doi.org/10.1007/s00345-024-04824-6 . Alder R, Zetner D, Rosenberg J. Incidence of Inguinal Hernia after Radical Prostatectomy: A Systematic Review and Meta-Analysis. J Urol. 2020;203(2):265–74. https://doi.org/10.1097/ju.0000000000000313 . Hakozaki Y, Yamada Y, Fujimura T, Kimura N, Sasaki K, Maki K, Sugimoto K, Izumi T, Kaneko J, Urabe F, Tokunaga M, Fujii Y, Kamei J, Kawai T, Taguchi S, Akiyama Y, Yamada D, Kume H. Novel clipping procedure for preventing post-operative inguinal hernia in robot‐assisted radical prostatectomy. Int J Urol. 2024;31(11):1241–7. https://doi.org/10.1111/iju.15544 . Chang KD, Abdel Raheem A, Santok GDR, Kim LHC, Lum TGH, Lee SH, Ham WS, Choi YD, Rha KH. Anatomical Retzius-space preservation is associated with lower incidence of postoperative inguinal hernia development after robot-assisted radical prostatectomy. Hernia. 2017;21(4):555–61. https://doi.org/10.1007/s10029-017-1588-9 . Liu L, Xu H, Qi F, Wang S, Shadhu K, Ramlagun-Mungur D, Wang S. Incidence and risk factors of inguinal hernia occurred after radical prostatectomy-comparisons of different approaches. BMC Surg. 2020;20(1):218. https://doi.org/10.1186/s12893-020-00883-9 . Yu W, Ma Y, Wu J, Zhang M, Yang C. Interpretable machine learning model predicts 1-year inguinal hernia risk after robot-assisted radical prostatectomy. J Robotic Surg. 2025;19(1):564. https://doi.org/10.1007/s11701-025-02723-5 . Stranne J, Johansson E, Nilsson A, Bill-Axelson A, Carlsson S, Holmberg L, Johansson JE, Nyberg T, Ruutu M, Wiklund NP, Steineck G. Inguinal Hernia After Radical Prostatectomy for Prostate Cancer: Results From a Randomized Setting and a Nonrandomized Setting. Eur Urol. 2010;58(5):719–26. https://doi.org/10.1016/j.eururo.2010.08.006 . Xiang AP, Shen YF, Shen XF, Shao SH. Correlation between the incidence of inguinal hernia and risk factors after radical prostatic cancer surgery: a case control study. BMC Urol. 2024;24(1):131. https://doi.org/10.1186/s12894-024-01493-w . Kanda T, Fukuda S, Kohno Y, Fukui N, Kageyama Y. The processus vaginalis transection method is superior to the simple prophylactic procedure for prevention of inguinal hernia after radical prostatectomy. Int J Clin Oncol. 2015;21(2):384–8. https://doi.org/10.1007/s10147-015-0881-9 . Bakker WJ, Roos MM, Meijer RP, Burgmans JPJ. Influence of previous laparo-endoscopic inguinal hernia repair on performing radical prostatectomy: a nationwide survey among urological surgeons. Surg Endosc. 2020;35(6):2583–91. https://doi.org/10.1007/s00464-020-07676-4 . Otaki T, Hasegawa M, Yuzuriha S, Hanada I, Nagao K, Umemoto T, Shimizu Y, Kawakami M, Nakajima N, Kim H, Nitta M, Hanai K, Kawamura Y, Shoji S, Miyajima A. Clinical impact of psoas muscle volume on the development of inguinal hernia after robot-assisted radical prostatectomy. Surg Endosc. 2020;35(7):3320–8. https://doi.org/10.1007/s00464-020-07770-7 . Lin Y, Johnson LA, Fennessy FM, Turkbey B. Prostate Cancer Local Staging with Magnetic Resonance Imaging. Radiol Clin North Am. 2024;62(1):93–108. https://doi.org/10.1016/j.rcl.2023.06.010 . Magnetta MJ, Catania R, Girometti R, Westphalen AC, Borhani AA, Furlan A. Prostate MRI: staging and decision-making. Abdom Radiol. 2020;45(7):2143–53. https://doi.org/10.1007/s00261-020-02431-8 . Hu C, Qiao X, Huang R, Hu C, Bao J, Wang X. Development and Validation of a Multimodality Model Based on Whole-Slide Imaging and Biparametric MRI for Predicting Postoperative Biochemical Recurrence in Prostate Cancer. Radiology: Imaging Cancer. 2024;6(3):e230143. https://doi.org/10.1148/rycan.230143 . Zou B-Z, Wen H, Luo H-J, Luo W-C, Xie Q-T, Zhou M-T. Value of serum free prostate-specific antigen density in the diagnosis of prostate cancer. Ir J Med Sci. 2023;192(6):2681–7. https://doi.org/10.1007/s11845-023-03448-w . Li Q, Yang Z, Wang Z, Sun J, Wen C, Yan H, Shen H, Wang W, Xu B, Xiang J, Teng X, Zhang C, Zheng X, Xie L. The influence of prostate volume on pathological outcomes after radical prostatectomy: A single-center retrospective study. Medicine. 2023;102(49):e36526. https://doi.org/10.1097/md.0000000000036526 . Stone NN, Crawford ED, Skouteris VM, Arangua P, Metsinis P-M, Lucia MS, La Rosa FG, Werahera PN. The Ratio of the Number of Biopsy Specimens to Prostate Volume (Biopsy Density) Greater Than 1.5 Improves the Prostate Cancer Detection Rate in Men Undergoing Transperineal Biopsy of the Prostate. J Urol. 2019;202(2):264–71. https://doi.org/10.1097/ju.0000000000000204 . Haga N, Takinami R, Tanji R, Onagi A, Matsuoka K, Koguchi T, Akaihata H, Hata J, Ogawa S, Kataoka M, Sato Y, Ishibashi K, Aikawa K, Kojima Y. Comprehensive approach for post-prostatectomy incontinence in the era of robot-assisted radical prostatectomy. Fukushima J Med Sci. 2017;63(2):46–56. https://doi.org/10.5387/fms.2017-15 . Shimbo M, Endo F, Matsushita K, Iwabuchi T, Fujisaki A, Kyono Y, Hishiki K, Muraishi O, Hattori K. Incidence, Risk Factors and a Novel Prevention Technique for Inguinal Hernia after Robot-Assisted Radical Prostatectomy. Urol Int. 2017;98(1):54–60. https://doi.org/10.1159/000448339 . Mazaheri Y, Goldman DA, Di Paolo PL, Akin O, Hricak H. Comparison of Prostate Volume Measured by Endorectal Coil MRI to Prostate Specimen Volume and Mass After Radical Prostatectomy. Acad Radiol. 2015;22(5):556–62. https://doi.org/10.1016/j.acra.2015.01.003 . Bezinque A, Moriarity A, Farrell C, Peabody H, Noyes SL, Lane BR. Determination of Prostate Volume. Acad Radiol. 2018;25(12):1582–7. https://doi.org/10.1016/j.acra.2018.03.014 . Cuocolo R, Comelli A, Stefano A, Benfante V, Dahiya N, Stanzione A, Castaldo A, De Lucia DR, Yezzi A, Imbriaco M. Deep Learning Whole-Gland and Zonal Prostate Segmentation on a Public MRI Dataset. J Magn Reson Imaging. 2021;54(2):452–9. https://doi.org/10.1002/jmri.27585 . Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 09 May, 2026 Reviews received at journal 26 Apr, 2026 Reviewers agreed at journal 26 Apr, 2026 Reviewers agreed at journal 25 Apr, 2026 Reviewers agreed at journal 24 Apr, 2026 Reviewers invited by journal 24 Apr, 2026 Editor assigned by journal 23 Apr, 2026 Editor invited by journal 02 Apr, 2026 Submission checks completed at journal 01 Apr, 2026 First submitted to journal 01 Apr, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9224900","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":634272599,"identity":"fd1f7fee-64f0-47e0-a454-991245885970","order_by":0,"name":"Jiawei Zhang","email":"","orcid":"","institution":"First Affiliated Hospital of Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiawei","middleName":"","lastName":"Zhang","suffix":""},{"id":634272601,"identity":"d0827906-02b1-4708-9b9a-ffcf65c65358","order_by":1,"name":"Xuesheng Fan","email":"","orcid":"","institution":"The Lu' an Hospital Affiliated to Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xuesheng","middleName":"","lastName":"Fan","suffix":""},{"id":634272604,"identity":"03b8704a-3903-4910-9eea-65d3f8906c83","order_by":2,"name":"Weiwei Sheng","email":"","orcid":"","institution":"First Affiliated Hospital of Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Weiwei","middleName":"","lastName":"Sheng","suffix":""},{"id":634272605,"identity":"ab8db503-0f56-4680-b4be-047e383dbefc","order_by":3,"name":"Maoming Xiong","email":"","orcid":"","institution":"First Affiliated Hospital of Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Maoming","middleName":"","lastName":"Xiong","suffix":""},{"id":634272606,"identity":"cdf05e70-f2f3-4d51-bddb-c233fe41965f","order_by":4,"name":"Lisheng Wu","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Lisheng","middleName":"","lastName":"Wu","suffix":""},{"id":634272611,"identity":"d076b2d4-05ec-4ab4-9408-c768f67b7546","order_by":5,"name":"Guodong Cao","email":"","orcid":"","institution":"First Affiliated Hospital of Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Guodong","middleName":"","lastName":"Cao","suffix":""},{"id":634272614,"identity":"ec6eeac7-1be9-49d5-827a-30cc51bf7818","order_by":6,"name":"Xiaoqing Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYJACZhDBz97AcIA0LZI9B4BaEkjRYnADpJwYLQbHE5g/F9TcsWu4+fzhgZ8/GOT5G5ifPcCnRbLnAYPxjGPPkhtn5xgc7ElgMJxxgM3cAJ8WfokEhmQetsPJzNI5DAd4EhgYNzDwsEng08IG1HKY59/hZDbJ4w8O/klgsCeoBWgLYzNv22E7HgkGg8NAWxIJapHsedjMzNt3OEGCJ8fgsEyaRPKMw2xmeLUYHE8+/Jnn22F7++PHH398Y2Nj29/e/AyvFgaGxAYEycAgAY0mvCABTNoTVDcKRsEoGAUjFwAAINZF4k0K6KEAAAAASUVORK5CYII=","orcid":"","institution":"Shenzhen Institutes of Advanced Technology","correspondingAuthor":true,"prefix":"","firstName":"Xiaoqing","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-03-25 15:23:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9224900/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9224900/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108977501,"identity":"70b4da3d-977c-42e7-a008-51bee7f43d5a","added_by":"auto","created_at":"2026-05-11 11:31:56","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":57098,"visible":true,"origin":"","legend":"\u003cp\u003eMeasurement of prostate diameter when using the ellipsoid formula to calculate MRI-PV. (a) Maximum transverse diameter (Ax-W) and maximum longitudinal length(Ax-H) measured on axial T2W-MRI; (b) Maximum longitudinal (Sag-H) and maximum lateral length (Sag-W) measured on mid-sagittal T2W-MRI.\u003c/p\u003e\n\u003cp\u003eT2W=T2 weighted; MRI=magnetic resonance imaging.\u003c/p\u003e","description":"","filename":"image1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-9224900/v1/8a04eaeb212aedeadaa4443e.jpeg"},{"id":108976918,"identity":"4b056a76-2844-4cf6-afe6-7565789d9c6e","added_by":"auto","created_at":"2026-05-11 11:29:37","extension":"jpeg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":69226,"visible":true,"origin":"","legend":"\u003cp\u003eThe flowchart of deep segmentation network for preoperative prostate MRI segmentation and automated prostate MRI parameter extraction\u003c/p\u003e","description":"","filename":"image2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-9224900/v1/352d99d4ad1b408d6cd220aa.jpeg"},{"id":109204176,"identity":"33009fa9-ce61-46a5-b4a3-658912004b74","added_by":"auto","created_at":"2026-05-13 14:54:54","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":473529,"visible":true,"origin":"","legend":"\u003cp\u003eKaplan-Meier curve showing the proportion of PIH-free patients among different groups who underwent RARP. (a) PIH-free patients among with TNM (≤T2) and TNM (≥T3); (b) Sag-H (≤5.095cm) and Sag-H (\u0026gt;5.095cm) groups; (c) Sag-W (≤4.301cm) and Sag-W (\u0026gt;4.301cm) groups; (d) MRI-PV (≤67.490ml)and MRI-PV (\u0026gt;67.490ml) groups.\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-9224900/v1/8cf6a65180453dbe5811a2fa.png"},{"id":108977385,"identity":"9d8b38df-ad6d-4540-934f-a6e5c537fb78","added_by":"auto","created_at":"2026-05-11 11:31:35","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":5539985,"visible":true,"origin":"","legend":"\u003cp\u003eScatterplot examination and linear regression analysis between different of prostate volume measurements in different groups. (a) MRI-PV compared with the PA-PV in the No-PIH group; (b) MRI-PV compared with the PA-PV in the PIH group; (c) the difference between MRI-PV and PA-PV compared with PA-PV.\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-9224900/v1/44fbda8de56fa81c81e8cd30.png"},{"id":108839070,"identity":"7b93f19e-279c-4eaf-90e5-880b67c7e878","added_by":"auto","created_at":"2026-05-09 00:40:41","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":338366,"visible":true,"origin":"","legend":"\u003cp\u003eBland-Altman plots show comparisons between different groups (a) MRI-PV and PA-PV in the No-PIH group; (b) MRI-PV and the PA-PV in the PIH group. U-LOA, upper limit of agreement; L-LOA, lower limit of agreement; MRI-PV, magnetic resonance imaging based prostate volume.\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-9224900/v1/78f4f0476dc917a01cb02528.png"},{"id":109206444,"identity":"5cea6768-90a7-4d28-9078-d60b9c7ea27d","added_by":"auto","created_at":"2026-05-13 15:12:49","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":17499646,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9224900/v1/9718aba2-17ea-4406-969d-1608cc161659.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Application of Deep Learning for Preoperative prostate MRI segmentation in Postoperative Inguinal Hernia Prediction after robot-assisted radical prostatectomy","fulltext":[{"header":"Introduction","content":"\u003cp\u003eProstate cancer (PC) is one of the most common cancers among men in the world [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Radical prostatectomy (RP) has been considered as the gold-standard treatment for PC. Over time, surgical techniques for RP have evolved from open surgery to laparoscopy, and now to robot-assisted laparoscopic radical prostatectomy (RARP). RARP has recently gained widespread popularity over open or traditional laparoscopic surgery worldwide, with a significant increase in the number of cases. This widely used application is attributed to the inherent advantages of a minimally invasive approach and the enhanced dexterity it offers in the confined pelvic space.\u003c/p\u003e\u003cp\u003eAlthough it is acknowledged that RP surgical techniques are effective and safe, several postoperative complications can occur, such as urinary incontinence and erectile dysfunction [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. In recent years, PIH has attracted increasing attention from surgeons as a major complication, mainly because it is a common disease in the aging male population [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Previous research has shown that the incidence of PIH after open retropubic radical prostatectomy (ORP) ranges from 10% to 24% in the first several postoperative years after surgery, in contrast, the occurrence rates of PIH are lower after laparoscopic radical prostatectomy (LRP), ranging from 5.3% to 14.0% [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Additionally, previous studies had reported that the incidence of PIH is higher in patients who undergo RARP compared to those who do not [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. However, these studies had not provided specific incidences or identified the risk factors for PIH after RARP. \u003cb\u003eFurthermore\u003c/b\u003e, patients with PIH typically require surgical treatment with additional mesh, which increases the duration of operation and the risk of anesthesia [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. This significantly affects the patient's quality of life and increases the financial burden on medical insurance. Therefore, how to predict the occurrence of PIH so as to take preventive measures have significant clinical significance.\u003c/p\u003e\u003cp\u003eMagnetic resonance imaging (MRI) is one of the most important medical imaging techniques for the diagnosis and therapeutic effect detection of PC [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. The Prostate Imaging Reporting and Data System (PIRADS) provides a standardized framework for reporting and evaluating prostate MRI [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. However, applying this system requires experienced radiologists and is time-consuming. Some studies have developed scoring systems based on PIRADS to predict whether patients with PC need surgical treatment [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Multiparametric MRI scans have also been shown to improve surgical decision-making for nerve-sparing versus non\u0026ndash;nerve-sparing approaches, thereby helping to prevent postoperative complications such as urinary incontinence and erectile dysfunction after RP [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. In addition, several studies have predicted patient survival using prostate MRI parameters in combination with pathological results [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Nevertheless, few studies have investigated the prediction of PIH by fully exploiting the potential of preoperative MRI parameters.\u003c/p\u003e\u003cp\u003eRecently, deep learning (DL) techniques have emerged as a promising tool for various medical applications, including image segmentation and medical image feature extraction [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. Previous studies have demonstrated that MRI-based DL models can effectively assess PC risk and predict clinical outcomes by integrating imaging features and clinical factors [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. However, the application of MRI-based DL models in predicting PIH based on preoperative prostate MRI remained underexplored. This study aimed to investigate the potential of the MRI-based DL models for the prediction of PIH following RARP and identify specific risk MRI factors. This can ultimately assist surgeons in implementing appropriate preventive measures during RP.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cdiv id=\"Sec2\" class=\"Section2\"\u003e \u003ch2\u003eData preparation\u003c/h2\u003e \u003cp\u003e This study was approved by the Ethics Committee of the First Affiliated Hospital of Anhui Medical University (No. PJ2024-11-62), Hefei, China. We retrospectively analyzed 540 consecutive patients who underwent RARP at First Affiliated Hospital of Anhui Medical University in eastern China between January 2020 and December 2024. All patients underwent MRI examinations within one month before the operation, and written informed consents were provided by all patients. This study was performed following the Declaration of Helsinki.\u003c/p\u003e \u003cp\u003eExclusion criteria of patients: (1) Conservative treatment or endocrine therapy for advanced metastatic prostate cancer. (2) All patients who have previously undergone surgical treatment for inguinal hernia (IH) or currently have concurrent IH. (3) Preoperative radiotherapy and chemotherapy or previous urethral prostatectomy. (4) Severe preoperative pulmonary function abnormalities. (5) Patients with cirrhotic ascites and uremia undergoing peritoneal dialysis. (6) The case imaging data are incomplete. (7) Follow-up loss of contact.\u003c/p\u003e \u003cp\u003eTo detect subclinical preoperative IH as much as possible and increase the reliability of this study, we retrospectively examined preoperative MRI scans for transverse fascial weakness and reviewed all intraoperative videos during RARP to check whether there was a combined status of subclinical IH. Finally, a total of 540 patients were included in this study. The clinical baseline data of the patients are listed in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eSurgical procedures and medical follow-up protocol\u003c/h2\u003e \u003cp\u003eAll RARPs were performed with a DaVinci Robot Surgical System (Intuitive Surgical G.K., USA). Standard techniques of the operative procedures were performed with a trans-peritoneal approach. The space of Retzius was dissected. Obturator lymph node dissection was performed for patients with moderate risk, and extended lymph node dissection was positively performed in high risk patients. Neurovascular bundle preservation was strictly attempted in patients without the presence of cancer at the peripheral margin in order to preserve the patients' sexual function. The procedures were performed by experienced surgical team with an annual surgical volume of over 50 RARP cases. Postoperative follow-up were conducted at 1, 3, 6, 9 ,and 12months in the first year, then every 6 months as a routine procedure. PIH was diagnosed based on clinical symptoms, a physical examination and results of ultrasound examination in the inguinal area.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eThe Development of Deep Learning for Preoperative prostate MRI segmentation and prostate MRI parameter extraction\u003c/h3\u003e\n\u003cp\u003eMRI examinations were conducted using a 3.0T MRI system (Discovery 750, GE Healthcare). The MRI scan sequences included axial, coronal, and sagittal propeller FR FSE T2WI covering the prostate apex to base and seminal vesicles. The maximum longitudinal length (Ax-H) and the maximum transverse length of the prostate (Ax-W), was measured on axial T2-weighted images (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003ea) and the maximum longitudinal (Sag-H) and maximum lateral length (Sag-W) were measured on mid-sagittal T2-weighted images (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003eb). All patients\u0026rsquo; MRI-PV was calculated by the ellipsoid formula (Volume\u0026thinsp;=\u0026thinsp;Sag-H * Sag-W * Ax-W * π/6).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eWe implement a deep segmentation network U-Net architecture for preoperative prostate MRI segmentation by using Python and PyTorch. The AX mode dataset was collected to train U-Net consists of 1,181 images from 197 patients, with 29 patients having PIH and 168 healthy controls (HC). The dataset is split at the participant level into a training set and a testing set with a ratio of 8:2, as offered in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. The experiments are run on an NVIDIA TITAN V GPU, and the Adam optimizer with default parameter settings is utilized to optimize the U-Net. The training epochs, batch size, and initial learning rate are set to 100, 8, and 0.00015. The Cosine Annealing LR scheduler is applied to adjust the learning rate. MRI images are resized to 256\u0026times;256 as the inputs for the U-Net (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe deep segmentation network achieved an accuracy of 98.95% in correctly segmenting the prostate MRI images. The prostate MRI image segmentation results are then used to extract preoperative prostate MRI parameters. To ensure precision, the segmented MRI images are checked twice, and any MRI images with segmentation errors are manually corrected.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePreoperative prostate MRI segmentation dataset distribution\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"8\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003eTraining\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c6\" namest=\"c5\"\u003e \u003cp\u003eTest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c8\" namest=\"c7\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImages\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eParticipants\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eImages\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eParticipants\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eImages\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003eParticipants\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eAX\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo-PIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e779\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e130\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e228\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1007\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e168\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e162\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e174\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eSAG\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo-PIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e804\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e134\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e198\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1002\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e167\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePIH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e132\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e174\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eContinuous variables were described as mean and standard deviation. An independent \u003cem\u003et-\u003c/em\u003etest or Mann-Whitney U test was used to investigate the significant difference of continuous variables between two groups. Categorical variables were described as numbers and percentages. The \u003cem\u003eχ2\u003c/em\u003e test /Fisher's exact test was used to compare categorical variables. A two-tailed value of \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant. Univariate and multivariate logistic regression analyses were employed to identify the risk factors of PIH, and the odds ratio (OR) and 95% confidence interval (CI) were calculated. Pearson correlation analysis was used to construct correlation coefficients between MRI-PV and PA-PV. Linear regression analysis was used to calculate the variability in the MRI-PV and PA-PV. The Bland-Altman plot was applied to show the relationship between MRI-PV and PA-PV. All statistical analysis is conducted using IBM SPSS (version 26.0; IBM Corporation, Armonk, New York, USA). All graphs were created by using GraphPad Prism software version 9.5 (GraphPad Software, La Jolla, CA, USA).\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eDemographics and clinical characteristics of patients\u003c/h2\u003e \u003cp\u003eA total of 540 patients who underwent RARP were included in this study. The demographics and clinical characteristics of patients are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. All operations were performed via transperitoneal or retropubic approach by using the Da Vinci surgical robot system. The average operation time was 196.4\u0026thinsp;\u0026plusmn;\u0026thinsp;46.5 mins, and the median follow-up time was 15.3\u0026thinsp;\u0026plusmn;\u0026thinsp;6.6 months. Among them, 61 cases (11.3%) with PIH were treated as the PIH group. The remaining 479 cases (88.7%) were taken as the control group. Among the PIH group, there were 60 cases of indirect hernia, and there was 1 case of direct hernia. The demographics and clinical characteristics of all patients were shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. There were no statistically significant differences between the two groups in terms of age, BMI index, smoking history, drinking history, diabetes, preoperative PSA level, operation time, Gleason score, intraoperative pelvic lymph node dissection (PLND), and pathological N stage. The T stage of postoperative pathology and PA-PV showed significant differences between the two groups of patients (\u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThe PIH-free survival rates at 1 and 2 years after RARP were 91.11% and 89.26%, respectively. The average onset time of PIH was (7.8\u0026thinsp;\u0026plusmn;\u0026thinsp;5.8) months after operation. The PIH-free rate at 1, 2, and 3 years postoperatively was 85.9%, 79.6%, and 79.6% among patients with TMN(\u0026ge;\u0026thinsp;T3), and 91.6%, 89.5%, and 88.2% among patients with TMN(\u0026le;\u0026thinsp;T2) (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.017\u003c/em\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003ea).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDemographics and clinical characteristics of patients\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eBaselinel characteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eOverall(540)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003ePostoperative inguinal hernia\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cem\u003eχ\u0026sup2;/t\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cem\u003ep-value\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYes(n\u0026thinsp;=\u0026thinsp;61)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNo(n\u0026thinsp;=\u0026thinsp;479)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge(years)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e0.296\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.586\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e121(22.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12(19.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e109(22.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e419(77.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e49(80.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e370(77.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBMI(kg/m\u0026sup2;)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e3.086\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.214\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;18.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27(5.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4(6.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e23(4.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e18.5\u0026ndash;25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e346(64.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e44(72.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e302(63.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026gt;25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e167(31.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13(21.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e154(32.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSomking history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e0.009\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.924\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eyes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e55(10.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6(9.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e49(10.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eno\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e485(89.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e55(90.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e430(89.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDrinking history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e0.399\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.528\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eyes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e47(8.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4(6.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e43(9.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eno\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e493(91.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e57(93.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e436(91.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e0.358\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.550\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e85(15.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8(13.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e77(16.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e455(84.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e53(86.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e402(83.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreoperative PSA(ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e2.039\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.361\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e181(33.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e23(37.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e158(33.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e10\u0026ndash;20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e168(31.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e21(34.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e147(30.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026gt;20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e191(35.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e17(27.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e174(36.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreoperative Gleason grade\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e4.711\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.095\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026le;\u0026thinsp;6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e101(18.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12(19.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e89(18.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e250(46.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e35(57.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e215(44.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e189(35.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e14(22.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e175(36.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePLND\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e0.068\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.794\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eyes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e213(39.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e25(41.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e188(39.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eno\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e327(60.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e36(59.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e291(60.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOperation duration(mins)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e1.074\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.300\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;180\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e285(52.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e36(59.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e249(52.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;180\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e255(47.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e25(41.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e230(48.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePathological T stage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e6.674\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.010\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eT1-T2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e416 (77.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e39 (63.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e377 (78.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;T3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e124(23.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e22 (36.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e102 (21.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePathological N stage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e0.670\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cem\u003e0.413\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eN0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e489(90.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e57(93.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e432(90.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eN+\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e51(9.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4(6.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e47(9.8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePA-PV(ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003e5.92\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.015\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;63.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e405(75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e38(62.3%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e367(76.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026ge;\u0026thinsp;63.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e135(25%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e23(37.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e112(23.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cem\u003eBMI\u003c/em\u003e body mass index, \u003cem\u003eDM\u003c/em\u003e diabetes, \u003cem\u003ePSA\u003c/em\u003e prostate-specific antigen, \u003cem\u003ePLND\u003c/em\u003e Pelvic lymph node dissection, \u003cem\u003ePV\u003c/em\u003e prostate volume\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eMRI-based prostate parameters and MRI-PV\u003c/h2\u003e \u003cp\u003eAll MRI prostate parameters and MRI-PV statistics of the two groups were presented in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The Sag-H measured on the sagittal T2-weighted image was 5.065\u0026thinsp;\u0026plusmn;\u0026thinsp;0.891(cm) in the PIH group and 4.725\u0026thinsp;\u0026plusmn;\u0026thinsp;0.787(cm) in the non-PIH group. It was observed that there was a significant difference between the two groups (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.002\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e); the Sag-W was 4.360\u0026thinsp;\u0026plusmn;\u0026thinsp;0.693(cm) in the PIH group and 4.174\u0026thinsp;\u0026plusmn;\u0026thinsp;0.672(cm) in the non-PIH group (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.043\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). However, there were no significant differences in Ax-H (4.228\u0026thinsp;\u0026plusmn;\u0026thinsp;0.747 vs 4.250\u0026thinsp;\u0026plusmn;\u0026thinsp;0.643) (cm) and Ax-W (5.088\u0026thinsp;\u0026plusmn;\u0026thinsp;0.819 vs 4.994\u0026thinsp;\u0026plusmn;\u0026thinsp;0.750) (cm) on the axial T2-weighted images (\u003cem\u003ep\u0026thinsp;\u0026gt;\u0026thinsp;0.05\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The MRI-PV (62.250\u0026thinsp;\u0026plusmn;\u0026thinsp;27.264 vs 53.980\u0026thinsp;\u0026plusmn;\u0026thinsp;23.702) (ml), showing a significant difference between the two groups (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.012\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eMRI variables and prostate volume based MRI\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003ePIH\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eStatistic\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAx-H (cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.248\u0026thinsp;\u0026plusmn;\u0026thinsp;0.655\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.228\u0026thinsp;\u0026plusmn;\u0026thinsp;0.747\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e \u003cp\u003e4.250\u0026thinsp;\u0026plusmn;\u0026thinsp;0.643\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;0.250\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.802\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAx-W (cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e5.005\u0026thinsp;\u0026plusmn;\u0026thinsp;0.758\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e5.088\u0026thinsp;\u0026plusmn;\u0026thinsp;0.819\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e \u003cp\u003e4.994\u0026thinsp;\u0026plusmn;\u0026thinsp;0.750\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;0.915\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.361\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSag-H (cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.763\u0026thinsp;\u0026plusmn;\u0026thinsp;0.806\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e5.065\u0026thinsp;\u0026plusmn;\u0026thinsp;0.891\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e \u003cp\u003e4.725\u0026thinsp;\u0026plusmn;\u0026thinsp;0.787\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;3.736\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.002\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSag-W (cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.195\u0026thinsp;\u0026plusmn;\u0026thinsp;0.676\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.360\u0026thinsp;\u0026plusmn;\u0026thinsp;0.693\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e \u003cp\u003e4.174\u0026thinsp;\u0026plusmn;\u0026thinsp;0.672\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;2.026\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.043\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMRI-PV(ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e54.914\u0026thinsp;\u0026plusmn;\u0026thinsp;24.245\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e62.250. \u0026plusmn; 27.264\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e \u003cp\u003e53.980\u0026thinsp;\u0026plusmn;\u0026thinsp;23.702\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;2.522\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u003cb\u003e0.012\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eUnivariable and multivariable Logistic regression analyses for predictive factors of PIH\u003c/h3\u003e\n\u003cp\u003eIn the univariate Logistic regression analysis, the postoperative pathological T stage (\u0026ge;\u0026thinsp;T3) was a risk factor for PIH after RARP (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.011\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). The OR was 2.106(95%CI:1.192\u0026ndash;3.720). Compared with other MRI prostate parameters, such as Sag-H (\u0026gt;\u0026thinsp;5.095cm), Sag-W (\u0026gt;\u0026thinsp;4.301cm), and MRI-PV (\u0026gt;\u0026thinsp;67.490ml) were risk factors for PIH after RARP (\u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). The OR values were 1.909 (95%CI:1.087\u0026ndash;3.356), 1.784 (95%CI:1.041\u0026ndash;3.057) ,and 2.463 (95%CI:1.421\u0026ndash;4.269). In the multivariate Logistic regression analysis, the postoperative pathological T stage (\u0026ge;\u0026thinsp;T3) and MRI-PV (\u0026gt;\u0026thinsp;67.490ml) were risk factors for the occurrence of PIH (\u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/em\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e), and the adjusted OR values were 3.583 (95%CI:0.972\u0026ndash;13.210) and 1.772 (95%CI:1.036\u0026ndash;3.031).\u003c/p\u003e \u003cp\u003eThe PIH-free rate at 1, 2, and 3 years postoperatively was 85.5%, 79.8%, and 76.9% among patients with Sag-H (\u0026gt;\u0026thinsp;5.095cm), and 92.9%, 91.1%, and 91.1% among patients with Sag-H (\u0026le;\u0026thinsp;5.095cm) (\u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/em\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eb). The PIH-free rate at 2years postoperatively was 82.4% with Sag-W (\u0026gt;\u0026thinsp;4.301cm) and 90.5% with Sag-W (\u0026le;\u0026thinsp;4.301cm) (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.011\u003c/em\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003ec). The PIH-free rate at 2years postoperatively was 78.1% with MRI-PV (\u0026gt;\u0026thinsp;67.490ml) and 90.2% with MRI-PV (\u0026le;\u0026thinsp;67.490ml) (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.001\u003c/em\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003ed).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eUnivariate and multivariate analyses for the risk factors for PIH in patients with RARP\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eVariables\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eUnivariate analysis\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eMultivariate analysis\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eHR(95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eOR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHR(95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge(\u0026lt;65vs\u0026thinsp;\u0026ge;\u0026thinsp;65)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.203\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.618\u0026ndash;2.342\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.587\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.490\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBMI(kg/m\u0026sup2;)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.644\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.390\u0026ndash;1.065\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.086\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.293\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSomking history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.957\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.392\u0026ndash;2.338\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.924\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1.093\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDrinking history\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.712\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.246\u0026ndash;2.056\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.530\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.548\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.788\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.360\u0026ndash;1.723\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.551\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.217\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreoperative PSA(ng/ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.809\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.576\u0026ndash;1.137\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.222\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.914\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epreoperative Gleason grade\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.750\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.510\u0026ndash;1.104\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.145\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.811\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePLND\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.068\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.621\u0026ndash;1.836\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.813\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.054\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOpreation duration (\u0026lt;180min vs \u0026ge;\u0026thinsp;180min)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.752\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.438\u0026ndash;1.291\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.301\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.348\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePathological T stage (\u0026le;T2vs.\u0026ge;T3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.106\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.192\u0026ndash;3.720\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.011\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.583\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.972\u0026ndash;13.210\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u003cb\u003e0.045\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePathological N stage(N0 vs.N+)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.776\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.297\u0026ndash;2.030\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.606\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAx-H(cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.109\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.651\u0026ndash;1.890\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.703\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAx-W(cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.286\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.752\u0026ndash;2.198\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.358\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSag-H(cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.909\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.087\u0026ndash;3.356\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.025\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.934\u0026thinsp;~\u0026thinsp;4.373\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.074\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSag-W(cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.784\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.041\u0026ndash;3.057\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.035\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2.796\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.245\u0026ndash;31.941\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.408\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMRI-PV(ml)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2.463\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1.421\u0026thinsp;~\u0026thinsp;4.269\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e0.001\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3.776\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.136\u0026ndash;13.031\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e\u003cb\u003e0.037\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e\n\u003ch3\u003eComparison between MRI-PV and PA-PV\u003c/h3\u003e\n\u003cp\u003eThere was a high degree of correlation between MRI-PV and PA-PV in non-PIH group (r\u0026thinsp;=\u0026thinsp;0.870, \u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.01\u003c/em\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003ea), the same trend could also be observed in PIH group (r\u0026thinsp;=\u0026thinsp;0.923, \u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/em\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eb). MRI-PV overestimated PA-PV by 1.8ml in non-PIH group (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003ea), and 4.4ml in PIH group (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003eb). Linear regression analysis showed that the difference between MRI-PV and PA-PV was negatively related to PV (r= -0.415, \u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.01\u003c/em\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003ec\u003cem\u003e)\u003c/em\u003e. If PA-PV was \u0026lt;\u0026thinsp;63.25ml, MRI-PV overestimated PA-PV; if PA-PV was \u0026gt;\u0026thinsp;63.25ml, MRI-PV underestimated PA-PV (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003ec).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe Bland-Altman plots depict the relationship of the difference between MRI-PV and PA-PV, were shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e. The MAPE of MRI-PV was 18.93% in the non-PIH group (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003ea), 18.66% in the PIH group (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003eb). For the entire cohort, the number of people with percentage error within \u0026plusmn;l0% and \u0026plusmn;\u0026thinsp;20% were 194/540 (35.9%), and 396/540 (73.3%), respectively.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis study offered a unique means to measure PV for the occurrence of PIH prediction after RARP by using MRI-based DL models. Although RARP has improved the prognosis of urinary incontinence and erectile dysfunction compared to ORP, its impact on the incidence of PIH still remains controversial [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. The incidence of PIH after LRP has been previously reported to be lower than that after ORP [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. In recent years, with the wide use of surgical robots, the incidence of PIH after RARP has gradually become a hot research topic. Anatomical Retzius-space preservation is associated with a lower incidence of PIH development after RARP. Some studies have reported that the incidence of PIH after RARP ranges from 5.8% (18/577) to 10.8% (78/720) [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Our study retrospectively analyzed the clinical data, preoperative prostate MRI images ,and postoperative pathological reports of 540 patients admitted to our hospital and found that the overall incidence of inguinal hernia was 11.3% (61/540), which is close to the findings of most current studies. We also found that the average time of occurrence for PIH was 15.3\u0026thinsp;\u0026plusmn;\u0026thinsp;6.6 months, which has certain guiding significance for postoperative follow-up. In addition, few studies focused on the risk factors and preventive measures for PIH after RARP.\u003c/p\u003e \u003cp\u003eLiu L et al. found that patients who underwent retropubic radical prostatectomy were associated with an increased incidence of PIH, especially those over 80 years old [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Previous study from China showed that there was no statistically significant difference in age between the PIH group and No-PIH group of patients [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. In some regional studies, low BMI has been identified as a risk factor for PIH, with a dangerous threshold of BMI yet to be determined, approximately at BMI\u0026thinsp;\u0026lt;\u0026thinsp;25 kg/m\u0026sup2; [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. However, several studies have found that low BMI does not increase the occurrence risk of PIH [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. In the past years, bladder outlet obstruction (BOO) caused by post-RP anastomotic stricture, which leads to to PIH [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e], and Pelvic lymph node dissection(PLND) during RP can cause postoperative adhesion contraction of pelvic muscles, resulting in increased abdominal pressure in the inner ring orifice area and an increased incidence of PIH [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. After the popularization of robotic surgery, suturing, dissociation ,and PLND in narrow spaces were no longer difficult, and these factors might become insignificant. This study found that Age, BMI, PLND, hypertension, diabetes, PSA level, and operation duration were not statistically significant to occurrence of inguinal hernia after prostate cancer surgery (\u003cem\u003ep\u0026thinsp;\u0026gt;\u0026thinsp;0.05\u003c/em\u003e).\u003c/p\u003e \u003cp\u003eThe specific mechanism of PIH after radical prostatectomy is not yet clear. However, most methods predicted the occurrence of PIH that required intraoperative conditions and postoperative pathology, thereby limiting their application before the operation. How to use preoperative clinical data and imaging examinations to predict the occurrence of PIH and actively take preventive measures is noteworthy.\u003c/p\u003e \u003cp\u003eImaging examinations play a crucial role in the screening, diagnosis, and prognosis of PC. Some studies have utilized CT to observe indicators such as the psoas major muscle and rectus abdominis muscle to analyze the occurrence of PIH [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. These results suggested that the development of PIH is related to the strength and volume of abdominal wall muscles. However, due to the limitation of soft tissue visualization, CT was not as accurate as MRI in the detailed diagnosis and prognosis evaluation of PC. In the clinical process, MRI played a significant role in the treatment of PC. Previous studies have used preoperative MRI to assist in the diagnosis [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e], decision-making [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e] and predict postoperative survival of PC [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e] by observing various characteristics of the prostate, such as shape, size, and signal intensity. Among the various MRI prostate parameters, PV has been proven to be important for PC screening and prognosis evaluation [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. Previous clinical studies have confirmed that PA-PV is a significant indicator to help surgeons select the most appropriate treatment, reduce overtreatment of clinically insignificant PC, and predict lymph node invasion, biochemical recurrence, and clinical recurrence [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. In the daily work of active surveillance, PA-PV was divided by the number of biopsies to obtain the volume/biopsy ratio could determine the best predictors for positive biopsies [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]. Additionally, a larger prostate has a significant negative impact on to the PIH-free of post-prostatectomy incontinence despite undergoing the same RARP [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eHowever, few studies have investigated the relationship between MRI-PV and PIH. Previous research had found that due to the need for bladder-urethral anastomosis during prostatectomy, a comparison of preoperative and postoperative sagittal MRI images revealed a downward shift of the rectovesical (RE) pouch by approximately 2 to 3cm [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]. Therefore, we hypothesized that this downward shift of the RE pouch causes traction on the extraperitoneal tissues and vas deferens following urethral anastomosis, which in turn pulls the internal ring inward, alters pressure distribution within the myopectineal orifice, and contributes to the development of PIH.\u003c/p\u003e \u003cp\u003eThe factor influences the degree of RE downward shift is the prostate volume; the more severe the diseased prostate, the more pronounced the downward shift after resection, thus increasing the incidence of PIH. However, most of the experimental measurements of PA-PV were performed in vitro after surgery, which had certain limitations. Firstly, formalin fixation leads to tissue dehydration, which reduces the actual volume in vivo. Secondly, because PA-PV is measured postoperatively, preventive measures cannot be taken in time during the surgical operation. Historically, Planimetry-based assessment of PV was considered to be the closest to in vivo prostate size [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]. However, this method was time-consuming, cumbersome, required special software. Therefore, it was not widely used in daily clinical practice. Although less accurate than the Planimetry method, MRI-PV calculation using the ellipsoid formula has been widely used due to its effectiveness, accuracy, and radiation-free nature. Meanwhile, preoperative standardized assessment based on PI-RADS v2.1 was performed by experienced radiologists or trained specialists; this process is neither time-saving nor cost effective [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. In recent years, artificial intelligence has been increasingly applied to radiology, and relevant studies have confirmed the feasibility and effectiveness of automatic MRI segmentation based on deep learning algorithms [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]. However, the application of these deep learning models is largely limited to academic research rather than clinical applications. In this study, we utilized a deep learning-based automatic segmentation algorithm to measure preoperative prostate MRI parameters across different axes, estimate prostate volume using the ellipsoid formula, and evaluate its potential for predicting PIH occurrence. This method may enable early identification of high-risk patients undergoing RARP and facilitate timely preventive measures. However, the present study has certain limitations, and prospective multicenter trials are needed to further validate the predictive value of this method for PIH.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThe method using the automatic segmentation of a deep learning algorithm based on preoperative prostate MRI could measure the parameters of the prostate in different axes accurately. Larger specimen volume and higher T-stage maybe potential risk factors for the occurrence of PIH. Compared with traditional methods, this method has clinical significance due to its characteristics of lower cost and higher accuracy.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv id=\"AGS1\" class=\"AbbreviationGroupSection\"\u003e \u003cdiv class=\"Heading\"\u003eindex\u003c/div\u003e \u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAx-H\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003ethe maximum longitudinal length measured on axial T2-weighted images\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAx-W\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003ethe maximum transverse length measured on axial T2-weighted images\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003econfidence interval\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eDL\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003edeep learning\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eHC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003ehealthy controls\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eLRP\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003elaparoscopic radical prostatectomy\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eMRI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003emagnetic resonance imaging\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eOR\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003ethe odds ratio\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eORP\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eopen retropubic radical prostatectomy\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003ePC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eprostate cancer\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003ePLND\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003epelvic lymph node dissection\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003ePIH\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003epostoperative inguinal hernia\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003ePIRADS\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eprostate Imaging Reporting and Data System\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003ePV\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eprostate volume\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eRARP\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003erobot-assisted radical prostatectomy\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eRP\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eradical prostatectomy\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eSag-H\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003ethe maximum longitudinal length measured on mid-sagittal T2-weighted images\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eSag-W\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003ethe maximum lateral length measured on mid-sagittal T2-weighted images\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":" \u003cp\u003e \u003cstrong\u003eEthical approval and consent to participate\u003c/strong\u003e \u003cp\u003e Written informed consents were obtained by all patients before enrollment. This study was performed following the Declaration of Helsinki. Ethical approval was obtained from the Ethics Committee of the First Affiliated Hospital of Anhui Medical University (No. PJ2024-11-62), Hefei, China.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eConsent for publication\u003c/strong\u003e \u003cp\u003eNot applicable.\u003c/p\u003e \u003c/p\u003e\u003cp\u003e \u003ch2\u003eCompeting interests\u003c/h2\u003e \u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e \u003cp\u003eThis study was supported by the National Natural Science Foundation of China (Grant No. 82573191), Open Fund of Key Laboratory of Anti-inflammatory and Immune Medicine (Grant No.KFJJ-2023-10), Ministry of Education, P.R. China (Anhui Medical University), Higher education quality project of Anhui Province (Grant No. 2023jyxm1095) and Scientific Research Foundation of Education Department of Anhui Province of China (Grant No. 2025AHGXZK30334).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eThe study was conceived and designed by Jiawei Zhang, Xiaoqing Zhang, and Guodong Cao. Data were obtained by Xuesheng Fan and Weiwei Sheng. Data analysis and interpretation were performed by Xiaoqing Zhang and Jiawei Zhang. The manuscript was drafted by Jiawei Zhang, and revised by Xiaoqing Zhang, Maoming Xiong, Lisheng Wu, and Guodong Cao. All authors have read and commented on the working versions and approved the final manuscript before submission.\u003c/p\u003e\u003ch2\u003eAcknowledgements\u003c/h2\u003e \u003cp\u003eWe would like to express our gratitude to Zunjie Xiao from the Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, for his assistance with the statistical analysis in this study.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets used during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eHan B, Zheng R, Zeng H, Wang S, Sun K, Chen R, Li L, Wei W, He J. Cancer incidence and mortality in China, 2022. J Natl Cancer Cent. 2024;4(1):47\u0026ndash;53. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.jncc.2024.01.006\u003c/span\u003e\u003cspan address=\"10.1016/j.jncc.2024.01.006\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHamdy FC, Donovan JL, Lane JA, Metcalfe C, Davis M, Turner EL, Martin RM, Young GJ, Walsh EI, Bryant RJ, Bollina P, Doble A, Doherty A, Gillatt D, Gnanapragasam V, Hughes O, Kockelbergh R, Kynaston H, Paul A, Paez E, Powell P, Rosario DJ, Rowe E, Mason M, Catto JWF, Peters TJ, Oxley J, Williams NJ, Staffurth J, Neal DE. Fifteen-Year Outcomes after Monitoring, Surgery, or Radiotherapy for Prostate Cancer. N Engl J Med. 2023;388(17):1547\u0026ndash;58. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1056/NEJMoa2214122\u003c/span\u003e\u003cspan address=\"10.1056/NEJMoa2214122\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYatabe Y, Tanioka T, Waseda Y, Yamaguchi K, Ogo T, Fujiwara H, Okuno K, Kawada K, Haruki S, Tokunaga M, Fujii Y, Kinugasa Y. Inguinal hernia repair in patients with artificial urinary sphincter after radical prostatectomy. Hernia. 2024;28(4):1331\u0026ndash;6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10029-024-03040-w\u003c/span\u003e\u003cspan address=\"10.1007/s10029-024-03040-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAiolfi A, Bona D, Cal\u0026igrave; M, Manara M, Bonitta G, Cavalli M, Bruni PG, Carmignani L, Danelli P, Bonavina L, K\u0026ouml;ckerling F, Campanelli G. Is previous radical prostatectomy a contraindication to minimally invasive inguinal hernia repair? A contemporary meta-analysis. Hernia. 2024;28(5):1525\u0026ndash;36. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10029-024-03098-6\u003c/span\u003e\u003cspan address=\"10.1007/s10029-024-03098-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNilsson H, Stranne J, Hugosson J, Wessman C, Steineck G, Bjartell A, Carlsson S, Thorsteinsdottir T, Tyritzis SI, Lantz A, Wiklund P, Haglind E. Risk of hernia formation after radical prostatectomy: a comparison between open and robot-assisted laparoscopic radical prostatectomy within the prospectively controlled LAPPRO trial. Hernia. 2020;26(1):157\u0026ndash;64. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10029-020-02178-7\u003c/span\u003e\u003cspan address=\"10.1007/s10029-020-02178-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eToide M, Ebara S, Tatenuma T, Ikehata Y, Nakayama A, Kawase M, Sasaki T, Yoneda T, Sakaguchi K, Teishima J, Makiyama K, Kitamura H, Saito K, Koie T, Inoue T, Urakami S, Koga F. Incidence and risk factors of inguinal hernia after robot-assisted radical prostatectomy: a retrospective multicenter cohort study in Japan (the MSUG94 group). J Robotic Surg. 2024;18(1):38. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11701-023-01761-1\u003c/span\u003e\u003cspan address=\"10.1007/s11701-023-01761-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFunamizu N, Mineta SHO, Ozaki T, Mishima K, Igarashi K, Omura K, Takada Y, Wakabayashi GO. (2022) Utility of Robot-assisted Laparoscopic Transabdominal Preperitoneal Repair of Inguinal Hernia Following Robot-assisted Laparoscopic Radical Prostatectomy. In Vivo 36(3):1432\u0026ndash;1437. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.21873/invivo.12848\u003c/span\u003e\u003cspan address=\"10.21873/invivo.12848\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGiganti F, Dickinson L, Orczyk C, Haider A, Freeman A, Emberton M, Allen C, Moore CM. Prostate Imaging after Focal Ablation (PI-FAB): A Proposal for a Scoring System for Multiparametric MRI of the Prostate After Focal Therapy. Eur Urol Oncol. 2023;6(6):629\u0026ndash;34. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.euo.2023.04.007\u003c/span\u003e\u003cspan address=\"10.1016/j.euo.2023.04.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBerlin A, Brierley J, Cornford P, Chung P, Giannopoulos E, Mason M, Mottet N, Gospodarowicz M. TNM Staging of Prostate Cancer: Challenges in Securing a Globally Applicable Classification. Eur Urol. 2022;82(2):e52\u0026ndash;53. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.eururo.2022.04.019\u003c/span\u003e\u003cspan address=\"10.1016/j.eururo.2022.04.019\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTurkbey B, Rosenkrantz AB, Haider MA, Padhani AR, Villeirs G, Macura KJ, Tempany CM, Choyke PL, Cornud F, Margolis DJ, Thoeny HC, Verma S, Barentsz J, Weinreb JC. Eur Urol. 2019;76(3):340\u0026ndash;51. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.eururo.2019.02.033\u003c/span\u003e\u003cspan address=\"10.1016/j.eururo.2019.02.033\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePeters M, Eldred-Evans D, Kurver P, Falagario UG, Connor MJ, Shah TT, Verhoeff JJC, Taimen P, Aronen HJ, Knaapila J, Montoya Perez I, Ettala O, Stabile A, Gandaglia G, Fossati N, Martini A, Cucchiara V, Briganti A, Lantz A, Picker W, Haug ES, Nordstr\u0026ouml;m T, Tanaka MB, Reddy D, Bass E, van Rossum PSN, Wong K, Tam H, Winkler M, Gordon S, Qazi H, Bostr\u0026ouml;m PJ, Jambor I, Ahmed HU. Predicting the Need for Biopsy to Detect Clinically Significant Prostate Cancer in Patients with a Magnetic Resonance Imaging\u0026ndash;detected Prostate Imaging Reporting and Data System/Likert\u0026thinsp;\u0026ge;\u0026thinsp;3 Lesion: Development and Multinational External Validation of the Imperial Rapid Access to Prostate Imaging and Diagnosis Risk Score. Eur Urol. 2022;82(5):559\u0026ndash;68. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.eururo.2022.07.022\u003c/span\u003e\u003cspan address=\"10.1016/j.eururo.2022.07.022\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBahler CD, Tachibana I, Tann M, Collins K, Swensson JK, Green MA, Mathias CJ, Tong Y, Yong C, Boris RS, Brocken E, Hutchins GD, Sims JB, Hill DV, Smith N, Ferari C, Love H, Koch MO. Comparing Magnetic Resonance Imaging and Prostate-Specific Membrane Antigen\u0026ndash;Positron Emission Tomography for Prediction of Extraprostatic Extension of Prostate Cancer and Surgical Guidance: A Prospective Nonrandomized Clinical Trial. J Urol. 2024;212(2):290\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/ju.0000000000004032\u003c/span\u003e\u003cspan address=\"10.1097/ju.0000000000004032\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee HW, Kim E, Na I, Kim CK, Seo SI, Park H. Novel Multiparametric Magnetic Resonance Imaging-Based Deep Learning and Clinical Parameter Integration for the Prediction of Long-Term Biochemical Recurrence-Free Survival in Prostate Cancer after Radical Prostatectomy. Cancers. 2023;15(13):3416. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/cancers15133416\u003c/span\u003e\u003cspan address=\"10.3390/cancers15133416\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJiang Y, Zhou K, Sun Z, Wang H, Xie J, Zhang T, Sang S, Islam MT, Wang J-Y, Chen C, Yuan Q, Xi S, Li T, Xu Y, Xiong W, Wang W, Li G, Li R. Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics. Cell Rep Med. 2023;4(8):101146. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.xcrm.2023.101146\u003c/span\u003e\u003cspan address=\"10.1016/j.xcrm.2023.101146\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBeuque MPL, Lobbes MBI, van Wijk Y, Widaatalla Y, Primakov S, Majer M, Balleyguier C, Woodruff HC, Lambin P. Combining Deep Learning and Handcrafted Radiomics for Classification of Suspicious Lesions on Contrast-enhanced Mammograms. Radiology. 2023;307(5):e221843. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1148/radiol.221843\u003c/span\u003e\u003cspan address=\"10.1148/radiol.221843\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchrader A, Netzer N, Hielscher T, G\u0026ouml;rtz M, Zhang KS, Sch\u0026uuml;tz V, Stenzinger A, Hohenfellner M, Schlemmer H-P, Bonekamp D. Prostate cancer risk assessment and avoidance of prostate biopsies using fully automatic deep learning in prostate MRI: comparison to PI-RADS and integration with clinical data in nomograms. Eur Radiol. 2024;34(12):7909\u0026ndash;20. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00330-024-10818-0\u003c/span\u003e\u003cspan address=\"10.1007/s00330-024-10818-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePonsiglione A, Gambardella M, Stanzione A, Green R, Cantoni V, Nappi C, Crocetto F, Cuocolo R, Cuocolo A, Imbriaco M. Radiomics for the identification of extraprostatic extension with prostate MRI: a systematic review and meta-analysis. Eur Radiol. 2023;34(6):3981\u0026ndash;91. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00330-023-10427-3\u003c/span\u003e\u003cspan address=\"10.1007/s00330-023-10427-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmbrosini F, Knipper S, Tilki D, Heinzer H, Salomon G, Michl U, Steuber T, Pose RM, Bud\u0026auml;us L, Maurer T, Terrone C, Tennstedt P, Graefen M, Haese A. Robot-assisted vs open retropubic radical prostatectomy: a propensity score-matched comparative analysis based on 15 years and 18,805 patients. World J Urol. 2024;42(1):131. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00345-024-04824-6\u003c/span\u003e\u003cspan address=\"10.1007/s00345-024-04824-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlder R, Zetner D, Rosenberg J. Incidence of Inguinal Hernia after Radical Prostatectomy: A Systematic Review and Meta-Analysis. J Urol. 2020;203(2):265\u0026ndash;74. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/ju.0000000000000313\u003c/span\u003e\u003cspan address=\"10.1097/ju.0000000000000313\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHakozaki Y, Yamada Y, Fujimura T, Kimura N, Sasaki K, Maki K, Sugimoto K, Izumi T, Kaneko J, Urabe F, Tokunaga M, Fujii Y, Kamei J, Kawai T, Taguchi S, Akiyama Y, Yamada D, Kume H. Novel clipping procedure for preventing post-operative inguinal hernia in robot‐assisted radical prostatectomy. Int J Urol. 2024;31(11):1241\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/iju.15544\u003c/span\u003e\u003cspan address=\"10.1111/iju.15544\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChang KD, Abdel Raheem A, Santok GDR, Kim LHC, Lum TGH, Lee SH, Ham WS, Choi YD, Rha KH. Anatomical Retzius-space preservation is associated with lower incidence of postoperative inguinal hernia development after robot-assisted radical prostatectomy. Hernia. 2017;21(4):555\u0026ndash;61. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10029-017-1588-9\u003c/span\u003e\u003cspan address=\"10.1007/s10029-017-1588-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu L, Xu H, Qi F, Wang S, Shadhu K, Ramlagun-Mungur D, Wang S. Incidence and risk factors of inguinal hernia occurred after radical prostatectomy-comparisons of different approaches. BMC Surg. 2020;20(1):218. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s12893-020-00883-9\u003c/span\u003e\u003cspan address=\"10.1186/s12893-020-00883-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu W, Ma Y, Wu J, Zhang M, Yang C. Interpretable machine learning model predicts 1-year inguinal hernia risk after robot-assisted radical prostatectomy. J Robotic Surg. 2025;19(1):564. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11701-025-02723-5\u003c/span\u003e\u003cspan address=\"10.1007/s11701-025-02723-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStranne J, Johansson E, Nilsson A, Bill-Axelson A, Carlsson S, Holmberg L, Johansson JE, Nyberg T, Ruutu M, Wiklund NP, Steineck G. Inguinal Hernia After Radical Prostatectomy for Prostate Cancer: Results From a Randomized Setting and a Nonrandomized Setting. Eur Urol. 2010;58(5):719\u0026ndash;26. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.eururo.2010.08.006\u003c/span\u003e\u003cspan address=\"10.1016/j.eururo.2010.08.006\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXiang AP, Shen YF, Shen XF, Shao SH. Correlation between the incidence of inguinal hernia and risk factors after radical prostatic cancer surgery: a case control study. BMC Urol. 2024;24(1):131. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1186/s12894-024-01493-w\u003c/span\u003e\u003cspan address=\"10.1186/s12894-024-01493-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKanda T, Fukuda S, Kohno Y, Fukui N, Kageyama Y. The processus vaginalis transection method is superior to the simple prophylactic procedure for prevention of inguinal hernia after radical prostatectomy. Int J Clin Oncol. 2015;21(2):384\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s10147-015-0881-9\u003c/span\u003e\u003cspan address=\"10.1007/s10147-015-0881-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBakker WJ, Roos MM, Meijer RP, Burgmans JPJ. Influence of previous laparo-endoscopic inguinal hernia repair on performing radical prostatectomy: a nationwide survey among urological surgeons. Surg Endosc. 2020;35(6):2583\u0026ndash;91. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00464-020-07676-4\u003c/span\u003e\u003cspan address=\"10.1007/s00464-020-07676-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOtaki T, Hasegawa M, Yuzuriha S, Hanada I, Nagao K, Umemoto T, Shimizu Y, Kawakami M, Nakajima N, Kim H, Nitta M, Hanai K, Kawamura Y, Shoji S, Miyajima A. Clinical impact of psoas muscle volume on the development of inguinal hernia after robot-assisted radical prostatectomy. Surg Endosc. 2020;35(7):3320\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00464-020-07770-7\u003c/span\u003e\u003cspan address=\"10.1007/s00464-020-07770-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLin Y, Johnson LA, Fennessy FM, Turkbey B. Prostate Cancer Local Staging with Magnetic Resonance Imaging. Radiol Clin North Am. 2024;62(1):93\u0026ndash;108. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.rcl.2023.06.010\u003c/span\u003e\u003cspan address=\"10.1016/j.rcl.2023.06.010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMagnetta MJ, Catania R, Girometti R, Westphalen AC, Borhani AA, Furlan A. Prostate MRI: staging and decision-making. Abdom Radiol. 2020;45(7):2143\u0026ndash;53. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s00261-020-02431-8\u003c/span\u003e\u003cspan address=\"10.1007/s00261-020-02431-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu C, Qiao X, Huang R, Hu C, Bao J, Wang X. Development and Validation of a Multimodality Model Based on Whole-Slide Imaging and Biparametric MRI for Predicting Postoperative Biochemical Recurrence in Prostate Cancer. Radiology: Imaging Cancer. 2024;6(3):e230143. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1148/rycan.230143\u003c/span\u003e\u003cspan address=\"10.1148/rycan.230143\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZou B-Z, Wen H, Luo H-J, Luo W-C, Xie Q-T, Zhou M-T. Value of serum free prostate-specific antigen density in the diagnosis of prostate cancer. Ir J Med Sci. 2023;192(6):2681\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/s11845-023-03448-w\u003c/span\u003e\u003cspan address=\"10.1007/s11845-023-03448-w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi Q, Yang Z, Wang Z, Sun J, Wen C, Yan H, Shen H, Wang W, Xu B, Xiang J, Teng X, Zhang C, Zheng X, Xie L. The influence of prostate volume on pathological outcomes after radical prostatectomy: A single-center retrospective study. Medicine. 2023;102(49):e36526. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/md.0000000000036526\u003c/span\u003e\u003cspan address=\"10.1097/md.0000000000036526\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStone NN, Crawford ED, Skouteris VM, Arangua P, Metsinis P-M, Lucia MS, La Rosa FG, Werahera PN. The Ratio of the Number of Biopsy Specimens to Prostate Volume (Biopsy Density) Greater Than 1.5 Improves the Prostate Cancer Detection Rate in Men Undergoing Transperineal Biopsy of the Prostate. J Urol. 2019;202(2):264\u0026ndash;71. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/ju.0000000000000204\u003c/span\u003e\u003cspan address=\"10.1097/ju.0000000000000204\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHaga N, Takinami R, Tanji R, Onagi A, Matsuoka K, Koguchi T, Akaihata H, Hata J, Ogawa S, Kataoka M, Sato Y, Ishibashi K, Aikawa K, Kojima Y. Comprehensive approach for post-prostatectomy incontinence in the era of robot-assisted radical prostatectomy. Fukushima J Med Sci. 2017;63(2):46\u0026ndash;56. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.5387/fms.2017-15\u003c/span\u003e\u003cspan address=\"10.5387/fms.2017-15\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShimbo M, Endo F, Matsushita K, Iwabuchi T, Fujisaki A, Kyono Y, Hishiki K, Muraishi O, Hattori K. Incidence, Risk Factors and a Novel Prevention Technique for Inguinal Hernia after Robot-Assisted Radical Prostatectomy. Urol Int. 2017;98(1):54\u0026ndash;60. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1159/000448339\u003c/span\u003e\u003cspan address=\"10.1159/000448339\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMazaheri Y, Goldman DA, Di Paolo PL, Akin O, Hricak H. Comparison of Prostate Volume Measured by Endorectal Coil MRI to Prostate Specimen Volume and Mass After Radical Prostatectomy. Acad Radiol. 2015;22(5):556\u0026ndash;62. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.acra.2015.01.003\u003c/span\u003e\u003cspan address=\"10.1016/j.acra.2015.01.003\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBezinque A, Moriarity A, Farrell C, Peabody H, Noyes SL, Lane BR. Determination of Prostate Volume. Acad Radiol. 2018;25(12):1582\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.acra.2018.03.014\u003c/span\u003e\u003cspan address=\"10.1016/j.acra.2018.03.014\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCuocolo R, Comelli A, Stefano A, Benfante V, Dahiya N, Stanzione A, Castaldo A, De Lucia DR, Yezzi A, Imbriaco M. Deep Learning Whole-Gland and Zonal Prostate Segmentation on a Public MRI Dataset. J Magn Reson Imaging. 2021;54(2):452\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1002/jmri.27585\u003c/span\u003e\u003cspan address=\"10.1002/jmri.27585\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Deep Learning, Inguinal Hernia, Robot-assisted radical prostatectomy","lastPublishedDoi":"10.21203/rs.3.rs-9224900/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9224900/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003ePurpose\u003c/h2\u003e \u003cp\u003ePostoperative inguinal hernia (PIH) is a common complication after radical prostatectomy and has attracted significant attention from surgeons due to the need for additional surgical treatment. This study aimed to identify risk factors for PIH after robot-assisted radical prostatectomy (RARP) and determine if MRI can be used as a potential predictor of PIH.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA retrospective case-control study was conducted to analyze the clinical data, preoperative prostate MRI images, and postoperative pathological reports of 540 patients who underwent RARP from January 2020 to December 2024. A deep segmentation network is employed to process preoperative prostate MRI images and extract prostate MRI parameters automatically. Logistic regression analysis is performed to identify independent risk MRI factors of PIH, and Kaplan-Meier analysis was used to investigate the survival curve without PIH after RARP.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe median follow-up time was 15.3\u0026thinsp;\u0026plusmn;\u0026thinsp;6.6 months, and a total of 61 (11.3%) patients developed PIH. There were significant differences in Sag-H and Sag-W measured on sagittal T2-weighted images (\u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/em\u003e). The MRI-based prostate volume (MRI-PV) (62.250\u0026thinsp;\u0026plusmn;\u0026thinsp;27.264 vs 53.980\u0026thinsp;\u0026plusmn;\u0026thinsp;23.702) (ml) showed a significant statistical difference between the two groups (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.012\u003c/em\u003e). In the univariate and multivariate logistic regression analysis, the postoperative pathological T stage (\u0026ge;\u0026thinsp;T3) was a significant risk factor for the occurrence of PIH (\u003cem\u003ep\u0026thinsp;=\u0026thinsp;0.011\u003c/em\u003e). Sag-H (\u0026gt;\u0026thinsp;5.095cm), Sag-W (\u0026gt;\u0026thinsp;4.301cm), and MRI-PV (\u0026gt;\u0026thinsp;67.490ml) were risk factors for PIH after RARP (\u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/em\u003e). There was a high correlation between MRI-PV and pathology-based prostate volume (PA-PV) in the PIH group (r\u0026thinsp;=\u0026thinsp;0.923, \u003cem\u003ep\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/em\u003e).\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eLarger PA-PV and higher T-stage are potential risk factors for the occurrence of PIH. Prostate MRI parameters such as Sag-H \u003cem\u003e(\u0026gt;\u0026thinsp;5.095cm\u003c/em\u003e), Sag-W (\u003cem\u003e\u0026gt;\u0026thinsp;4.301cm\u003c/em\u003e), and MRI-PV (\u003cem\u003e\u0026gt;\u0026thinsp;67.490ml\u003c/em\u003e) might be related to the occurrence of PIH. These indicators show significant promise in helping us take measures to prevent PIH occurrence.\u003c/p\u003e","manuscriptTitle":"Application of Deep Learning for Preoperative prostate MRI segmentation in Postoperative Inguinal Hernia Prediction after robot-assisted radical prostatectomy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-09 00:40:37","doi":"10.21203/rs.3.rs-9224900/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-09T18:19:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-27T02:32:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"269603455244118310346008568994090838763","date":"2026-04-26T09:27:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"259470249596937628760851040459200763196","date":"2026-04-25T05:15:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271561987601753862331279731985867849589","date":"2026-04-25T03:22:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-24T15:45:19+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-23T08:12:55+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-02T05:05:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-02T03:19:19+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2026-04-02T03:13:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9318b904-13ec-44d8-b3e7-d5b22f6c8b80","owner":[],"postedDate":"May 9th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-09T18:19:53+00:00","index":64,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-09T00:40:37+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-09 00:40:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9224900","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9224900","identity":"rs-9224900","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}