Predictive Value of 18 F-FDG PET/MRI Parameters for MYCN Amplification in High-Risk Neuroblastoma

Predictive Value of 18 F-FDG PET/MRI Parameters for MYCN Amplification in High-Risk Neuroblastoma | 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 Predictive Value of 18 F-FDG PET/MRI Parameters for MYCN Amplification in High-Risk Neuroblastoma Jiangtao Liang, Feng Li, Zhongxiang Ding, Bing Yan, Yanfang Zhu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8265732/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Background To investigate the clinical value of 18 F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging ( 18 F-FDG PET/MRI) parameters in predicting the MYCN gene amplification status in patients with high-risk neuroblastoma (HR-NB). Methods A retrospective analysis was conducted on 72 HR-NB patients who underwent 18 F-FDG PET/MRI examinations at our institution between December 2018 and December 2024. Based on MYCN genetic testing results, the patients were classified into the MYCN amplification group (MNA) and the non-amplification group (MYCN-NA). The clinical data of the patients and the imaging characteristics of the primary tumors were collected. The GE post-processing workstation was used to identify lesions, and quantitative parameters on PET/MRI images were semi-automatically extracted. Multivariable logistic regression analysis was employed to screen for independent predictive factors. Diagnostic performance was assessed using Receiver Operating Characteristic (ROC) curves by calculating the Area Under the Curve (AUC), sensitivity, and specificity. Calibration plot and Decision Curve Analysis (DCA) were used to evaluate the calibration and clinical utility of the models, respectively. A combined model was visualized using a nomogram. Results Multivariate logistic regression analysis identified tumor necrosis (P = 0.039, OR = 5.52; 95% CI: 1.091–27.916), age (P = 0.042, OR = 0.959; 95% CI: 0.920–0.999), and Total Lesion Glycolysis (TLG) (P = 0.011, OR = 1.004; 95% CI: 0.982–1.008) as independent predictive factors of MYCN amplification in HR-NB. ROC curve analysis demonstrated that the diagnostic performance of the combined model had superior diagnostic performance (AUC: 0.858, 95% CI: 0.756–0.929, Sensitivity: 0.724, Specificity: 0.930) compared to using necrosis alone (AUC: 0.648, 95% CI: 0.526–0.757, Sensitivity: 0.621, Specificity: 0.674), age alone (AUC: 0.724, 95% CI: 0.606–0.823, Sensitivity: 0.517, Specificity: 0.930), or TLG alone (AUC: 0.791, 95% CI: 0.679–0.878, Sensitivity: 0.724, Specificity: 0.837). Calibration curves and DCA further confirmed the optimal clinical utility of the combined model. Conclusion The prediction model integrating tumor necrosis, TLG, and age can effectively and non-invasively predict the MYCN amplification status in HR-NB patients, exhibiting good diagnostic efficacy and clinical application potential. 18F-FDG PET/MRI Neuroblastoma MYCN Amplification Figures Figure 1 Figure 2 Figure 3 Figure 4 Introduction Neuroblastoma (NB), originating from neural crest cells, is the most common extracranial solid tumor in children [ 1 ]. NB can arise anywhere along the sympathetic nervous chain, including the neck, chest, abdomen, pelvis, and other regions [ 2 ]. However, the adrenal glands are the most common primary site, while locations like the neck and pelvis are relatively less frequent [ 3 ]. NB is characterized by high malignancy and marked heterogeneity. Amplification of the MYCN proto-oncogene is a well-established independent predictor of poor prognosis. Approximately 20%-30% of HR-NB patients harbor MYCN amplification [ 4 ], often presenting with rapid tumor progression, widespread metastases, and resistance to conventional chemotherapy and radiotherapy [ 5 , 6 ]. Identifying patients with poor prognosis at diagnosis is crucial for timely intervention to improve outcomes and survival. MYCN amplification status is not only a key indicator for risk stratification but also essential for designing targeted therapy strategies [ 4 ]. However, current detection methods (e.g., fluorescence in situ hybridization and gene sequencing) rely on invasive tissue biopsies and cannot dynamically monitor changes in gene status, limiting their widespread clinical application. 123 I-metaiodobenzylguanidine (mIBG) scintigraphy is a well-established standard imaging modality for NB, with sensitivity and specificity both exceeding 90% [ 7 , 8 ]. Nevertheless, the lack of regulatory approval for 123 I in China hinders the widespread use of pre-treatment 123 I-mIBG scintigraphy for NB diagnosis [ 9 ]. According to guidelines for 123 I-MIBG scintigraphy and staging [ 5 ], 18 F-FDG PET/MRI serves as a complementary imaging technique, providing non-invasive information on tumor metabolism and microstructure, showcasing unique advantages in assessing tumor heterogeneity. Preliminary studies suggest that MYCN-amplified neuroblastomas exhibit higher glucose metabolic activity and specific diffusion characteristics, such as lower Apparent Diffusion Coefficient (ADC) values correlating with tumor cellularity and proliferative activity. However, current research predominantly focuses on PET/CT [ 10 ] or single MRI parameters, lacking systematic exploration of combined PET/MRI multi-parameter models. Furthermore, physiological uptake in pediatric tumors (e.g., bone marrow, thymus) and the complexity of imaging-genomic correlations remain major challenges for accurate prediction. This study moves beyond the limitations of single imaging modalities by integrating 18 F-FDG PET/MRI parameters with clinical data to construct a multi-modal imaging model for the non-invasive prediction of MYCN amplification status in HR-NB patients. This model holds promise as a non-invasive imaging biomarker alternative to invasive biopsy, potentially providing a new tool for dynamic monitoring of MYCN status and treatment response assessment [ 11 ], thereby offering important theoretical support for precise risk stratification and optimization of targeted therapy strategies in HR-NB. Methods Research subjects We retrospectively analyzed clinical data and PET/MRI images of 72 pediatric HR-NB patients treated at our institution between December 2018 and December 2024. Patients were classified according to the International Neuroblastoma Risk Group (INRG) classification system [ 12 ]. All children underwent complete PET/MRI examination before any treatment and were diagnosed with HR-NB confirmed by histopathology and genetic testing. Inclusion criteria were: pathologically confirmed neuroblastoma; newly diagnosed lesion without prior anti-tumor therapy; availability of clear pre-treatment whole-body PET/MRI images; PET/MR examination performed 40–60 minutes after radiopharmaceutical injection. Exclusion criteria were: PET or MRI images not meeting diagnostic standards (e.g., metal or motion artifacts); suspected inaccuracies in SUV values; patients with other concurrent systemic malignancies; patients who have received any form of treatment (such as radiotherapy, chemotherapy, etc.) before undergoing PET/MR examination. Collected imaging data included: Necrosis, Calcification, Hemorrhage, Mean diameter, Maximum Standardized Uptake Value (SUVmax), Mean Standardized Uptake Value (SUVmean), Peak Standardized Uptake Value (SUVpeak), Metabolic Tumor Volume (MTV), Total Lesion Glycolysis (TLG), Mean Apparent Diffusion Coefficient (ADCmean), Coefficient of Variation (COV), and Image-Defined Risk Factors (IDRFs). Provided clinical data included age, sex, primary tumor site, histology, and INRG stage. The International Neuroblastoma Risk Group Staging System (INRGSS) [ 13 ] and the International Neuroblastoma Pathology Classification [ 14 , 15 ] were used for staging and histologic classification, respectively. Based on MYCN amplification status, patients were divided into MYCN-amplified (MNA) and non-amplified (MYCN-NA) groups. Data collection was approved by the hospital's Medical Ethics Committee (Approval No: medical ethics [2025]008), with informed consent obtained from guardians. All procedures followed the principles of the Declaration of Helsinki. Instrumentation Imaging data were acquired using a United States GE Healthcare integrated Time-of-Flight(TOF) PET/MRI system (GE SIGNA, Wisconsin, USA). This system consists of a PET detector equipped with time - of - flight (TOF) technology (TOF - PET) and the latest - generation 750W 3.0T MRI device. The TOF-PET detector utilizes advanced solid-state silicon photomultipliers (SiPMs) and the latest LBS crystals. The radiopharmaceutical used was 18 F-fludeoxyglucose( 18 F-FDG). Data Analysis and Measurement All images were interpreted by three radiologists who possess more than a decade of experience in the diagnosis of pediatric tumors and hold certifications in MRI and nuclear medicine. They reached a consensus through discussion. The PET VCAR software within the GE Healthcare AW 4.6 post - processing workstation was utilized to measure various quantitative parameters. For image analysis, both visual analysis and semi - quantitative analysis methods were primarily adopted. Conventional semi-quantitative metabolic parameters obtained included SUVmax, SUVmean, SUVpeak, MTV, TLG, ADCmean, and COV, where ADCmean was the average of ADC values from three points within the solid tumor component, and COV = (Standard deviation of SUV / SUVmean) × 100. MYCN Status Detection MYCN status was determined using Fluorescence In Situ Hybridization (FISH) on formalin-fixed, paraffin-embedded samples obtained via biopsy or surgical resection. According to international consensus for molecular diagnostics in neuroblastoma, a target gene copy number equal to the chromosome 2 copy number was defined as negative (≤ 2); 3–9 copies as gain; and ≥ 10 copies (≥ 5 times the chromosome 2 count) as amplified [ 16 ]. Statistical Analysis Data processing and statistical analysis were performed using SPSS software V23.0 and R software V4.2.3. The Shapiro-Wilk test assessed normality. Normally distributed data are expressed as mean ± standard deviation and analyzed using the t-test. Non-normally distributed data are expressed as median (Q1, Q3) and analyzed using the Mann-Whitney U test. Categorical data were compared using the chi-square test or Fisher's exact test. Multivariate logistic regression analysis was used to select independent predictors. ROC curves assessed the diagnostic performance of individual predictors and the combined model for predicting risk, calculating the AUC, sensitivity, and specificity. Calibration plots and Decision Curve Analysis (DCA) determined the calibration and clinical utility of the models, respectively. The DeLong test compared the diagnostic performance of the models, with P < 0.05 considered statistically significant. The combined model was visualized using a nomogram. Reproducibility Assessment Three doctors conducted a consistency check on the qualitative features. As quantitative features were automatically extracted by the GE workstation, no consistency check was needed for them. The Kappa value was used as a measure of inter-observer consistency, with a Kappa value ≥ 0.75 indicating good consistency. Results Clinical Characteristics Clinical characteristics of all patients are summarized in Table 1 . The cohort comprised 72 patients, including 44 males and 28 females. Among them, 29 patients had MYCN amplification (MNA) group, while the remaining 43 were non-amplified (MYCN-NA) group. The mean ages were 37 months and 52 months, respectively, with the non-amplified group being significantly older ( p < 0.05). Most tumors were located in the adrenal glands (n = 49), with a smaller proportion observed in other regions (n = 23). The majority of patients (n = 58, 80.6%) had IDRFs present, while a minority (n = 14, 19.4%) did not. According to INRGSS, in the MYCN-NA group, 3 (7%) were stage L1, 8 (19%) were stage L2, and 32 (74%) were stage M. Conversely, in the MNA group, 2 (7%) were stage L2, and 27 (93%) were stage M. No significant differences were found between the amplified and non-amplified groups regarding Gender, Primary site, IDRFs, or Stage. Table 1 Clinical characteristics between the MYCN amplification group (MNA) and the non-amplification group (MYCN-NA). Variable MNA(n = 29) MYCN-NA(n = 43) 统计量 P值 Age(month) 37(8–96) 52(20–108) −3.048 0.003 Gender(n, %) 0.125 0.724 Male 17(59%) 27(63%) Female 12(41%) 16(37%) Primary site(n, %) 0.746 0.382 Adrenal gland 21(72%) 28(68%) Other 7(28%) 16(32%) IDRFs (n, %) 0.803 0.370 positive 21(72%) 37(84%) negative 7(28%) 7(16%) Stage (n, %) 4.471 0.107 L1 0(0%) 3(7%) L2 2(7%) 8(19%) M 27(93%) 32(74%) Ms 0(0%) 0(0%) IDRFs, Image-Defined Risk Factors. Multivariate Logistic Regression Analysis Combining Qualitative and Quantitative Features Results of the multivariate analysis incorporating clinical and quantitative features are shown in Table 2 . The analysis indicated that Thanatosis (P = 0.039, OR = 5.520, 95% CI: 1.091–27.916), Age (P = 0.042; OR = 0.959, 95% CI: 0.920–0.999), and TLG (P = 0.011; OR = 1.004, 95% CI: 0.982–1.008) were confirmed as independent predictors for the amplification group.The multivariate logistic analysis is depicted in a forest plot (Fig. 1 ). Table 2 Multivariate logistic regression analysis for the association between significant indices and MYCN amplification. Variable MNA MYCN-NA 统计量 P value Univariate analysis OR(95%CI) P value Thanatosis 7.473 0.006 5.520(1.091–27.916) 0.039 YES 19(65.5%) 14(32.6%) NO 10(34.5%) 29(67.4%) Calcification 4.416 0.036 0.374(0.068–2.071) 0.260 YES 17(58.6%) 35(81.4%) NO 12(41.4%) 8(18.6%) Hemorrhage 3.284 0.070 1.961(0.403–9.542) 0.404 YES 11(37.9%) 8(18.6%) NO 18(62.1%) 35(81.4%) Age(month) 24(17,48) 48(36, 6) 3.269 0.001 0.959(0.920–0.999) 0.042 Mean diameter(cm) 7.81 ± 2.81 7.08 ± 3.03 1.030 0.307 0.825(0.549–1.237) 0.352 SUV max 7.63 ± 2.96 7.39 ± 398 0.275 0.784 0.705(0.365–1.364) 0.299 SUV mean 4.46(3.17,5.06) 3.65(2.76, 4.92) 0.987 0.323 1.226(0.388–3.872 0.729 MTV(cm 3 ) 179.00(52.35, 314.50) 67.68(25.60, 155.00) 2.543 0.051 0.997(0.987–1.009) 0.712 TLG(g) 620.00(211.50, 1543.60) 223.80(67.70,440.80) 3.008 0.003 1.004(0.982–1.008) 0.011 ADCmean(×10⁻³mm²/s) 0.71(0.63, 0.83) 0.68(0.60, 0.78) -0.706 0.78 2.446(0.035–169.60) 0.679 COV 18.24 ± 2.23 18.98 ± 2.89 -1.156 0.252 0.957(0.746–1.227) 0.727 SUVmax, maximum standardized uptake value; SUVmean, mean standardized uptake value; MTV, tumor metabolic volume; TLG, total lesion glycolysis; ADCmean, mean Apparent Diffusion Coefficient; COV, coefficient of variation. Predictive Performance Evaluation of the Models The Youden Index from ROC analysis indicated optimal cut-off values of 24 months for Age and 479.7 for TLG. ROC curve analysis showed that the independent predictor TLG exhibited the highest predictive performance among individual parameters (AUC: 0.791, 95% CI: 0.679–0.878, Sensitivity: 0.724, Specificity: 0.837). Similarly, Age showed high predictive accuracy among clinical parameters (AUC: 0.724, 95% CI: 0.606–0.823, Sensitivity: 0.517, Specificity: 0.930). Tumor Necrosis was another independent predictor (AUC: 0.648, 95% CI: 0.526–0.757, Sensitivity: 0.621, Specificity: 0.674). The predictive model constructed by combining these three independent predictors showed improved diagnostic efficacy compared to using Necrosis, Age, or TLG alone, with an AUC of 0.858 (95% CI: 0.756–0.929, Sensitivity: 0.724, Specificity: 0.930) (Table 3 ). The DCA curves for the four models (Fig. 2 ) indicated that the combined model had the best clinical utility. The four models were evaluated using calibration curves (Fig. 3 ). The nomogram for the combined model is shown in Fig. 4 . Table 3 Discriminative diagnostic efficiency of significant parameters between MYCN amplified and non-amplified groups. Cut-off AUC (95% CI) Sensitivity (95% CI) Specificity (95% CI) P-value Thanatosis - 0.648(0.526–0.757) 0.621(0.423–0.793) 0.674(0.515–0.809) 0.011 Age(month) 24 0.724(0.606–0.823) 0.517(0.325–0.706) 0.930(0.809–0.985) <0.001 TLG 479.7 0.791(0.679–0.878) 0.724(0.528–0.873) 0.837(0.693–0.932) <0.001 Combined model - 0.858(0.756–0.929) 0.724(0.528–0.873) 0.930(0.809–0.985) <0.001 Reproducibility Assessment The consistency check for qualitative features is shown in Table 4 , indicating good inter-observer agreement, with Kappa values ranging from 0.762 to 0.806. Table 4 Consistency check results for qualitative features. Variable N (% of concordance) Kappa (95% CI) P value Thanatosis 65/72 0.806(0.669–0.943) <0.001 Calcification 62/72 0.762(0.562–0.882) <0.001 Hemorrhage 64/72 0.778(0.633–0.925) <0.001 Discussion Neuroblastoma (NB) is an embryonic tumor arising from neural crest cells, with malignant transformation possible at any stage of differentiation. NB is highly heterogeneous; some NB cells may grow slowly yet be highly malignant, while others grow rapidly but can spontaneously differentiate into benign forms or even regress [ 17 ]. MYCN amplification is a major driver of oncogenesis in NB, occurring in approximately 30%-40% of HR-NB patients and playing a crucial role in its initiation and early development [ 4 ]. This study is the first to elucidate the role of clinical characteristics and 18 F-FDG PET/MR imaging parameters in predicting MYCN amplification in HR-NB patients. Our findings indicate that MYCN amplification occurred in 40% of HR-NB patients, consistent with previous reports [ 4 ]. The results demonstrate that clinical features and metabolic parameters derived from 18 F-FDG PET/MR can effectively distinguish between MYCN-amplified and non-amplified HR-NB, with tumor necrosis, age, and TLG identified as independent predictors of MYCN amplification. Furthermore, we constructed a predictive model based on these three factors, which significantly enhanced the ability to discriminate MYCN amplification status. The significant association between tumor necrosis and MYCN amplification (OR = 5.52, P = 0.039) aligns with previous research linking necrotic areas to hypoxia-driven genomic instability and chemotherapy resistance in MYCN-amplified tumors [ 18 ]. Tumor necrosis reflects tumor proliferation outpacing its blood supply, a characteristic driven by MYCN oncogene activity [ 19 ]. In neuroblastoma, radiomics analyses have also identified necrotic patterns as predictors of poor prognosis, although their standalone predictive accuracy remains moderate (AUC: 0.648) [ 20 ]. The low sensitivity (62.1%) and specificity (67.4%) of necrosis alone for predicting MYCN amplification highlight the necessity of integrating metabolic parameters and clinical data for comprehensive risk assessment. Age was a risk factor for MYCN amplification (OR = 0.959, P = 0.042), consistent with epidemiological trends showing a peak incidence of MYCN amplification in children over 18 months [ 21 ]. Older age in neuroblastoma patients is generally associated with poorer outcomes compared to younger patients. However, research on age specifically for predicting MYCN amplification is limited [ 22 ]. Our study showed that age had high specificity (93.0%) but low sensitivity (51.7%) for predicting MYCN amplification, underscoring the need for multi-modal models to compensate for the limitations of using age alone [ 23 ]. This aligns with recent consensus guidelines in pediatric oncology advocating for combined clinical and imaging models [ 24 ]. Total Lesion Glycolysis (TLG), reflecting both glycolytic activity and tumor burden, exhibited the strongest individual predictive performance (AUC: 0.791). MYCN amplification is known to upregulate glucose metabolism via GLUT1 overexpression and hexokinase activation [ 25 ], and TLG quantifies this more comprehensively than static indices like SUVmax [ 26 ]. Our findings are consistent with Li et al. [ 27 ], who identified TLG as a key discriminator of MYCN status in HR-NB. However, the wide confidence interval for TLG's OR (95% CI: 0.982–1.008) suggests metabolic heterogeneity, emphasizing the need for supplemental biomarkers. The combined model incorporating tumor necrosis, age, and TLG achieved higher diagnostic accuracy (AUC: 0.858), outperforming individual parameters. This synergistic effect is analogous to advances in radiomics, where hybrid models integrating imaging and clinical data improve prognostic accuracy in radiogenomics [ 28 ]. For instance, Feng et al. [ 29 ] developed a PET/CT-based nomogram combining radiomic features with INRG stage, achieving comparable predictive ability (AUC: 0.840). Our calibration curves and DCA further validate the clinical utility of such models, offering a non-invasive alternative to biopsy for MYCN risk stratification [ 30 ]. Despite the positive results, this study has several limitations. First, the relatively small sample size may limit the generalizability of the model [ 31 ]. Second, the single-center design potentially introduces selection bias. Future studies are needed to validate this model in larger, multi-center patient cohorts. Future research should focus on: (1) validating the model's predictive power in larger patient populations; (2) exploring its applicability across different age and ethnic groups; (3) further optimizing the risk assessment model by incorporating radiomics data [ 32 , 33 ]. The future goal is to utilize large-sample, multi-center cohort studies to evaluate its value in distinguishing risk within INRGSS high-risk and non-high-risk groups. Conclusion In conclusion, the model based on qualitative and quantitative features from 18 F-FDG PET/MRI provides a novel method for differentiating MYCN amplification status in neuroblastoma patients. Compared to existing literature, this approach offers a more comprehensive and precise analysis of tumor characteristics and holds promise for widespread clinical application. Declarations Ethics approval and consent to participate Data collection was approved by the hospital's Medical Ethics Committee (Approval No: medical ethics [2025]008), with informed consent obtained from guardians. All procedures followed the principles of the Declaration of Helsinki. Consent for publication Not applicable. Competing interests The authors declare no competing interests. Author details 1 Hangzhou Universal Medical Imaging Diagnostic Center, No. 893 Jiangcheng Rd., Hangzhou, Zhejiang, China 2 Shanghai Universal Medical Imaging Diagnostic Center, No.8 Building, Huaxin Center, 406 Guilin Road, Xuhui District, Shanghai, China 3 Department of Radiology, Affiliated Hangzhou First People’s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang, China Funding This research is supported by Medical Science and Technology Project of Zhejiang Province(NO. 2022KY1047, 2024KY1428). Author Contribution 1. Liang and F. Li were responsible for the study design and wrote the main manuscript text. B. Yan, Y. Zhu and F. Wang conducted the data analysis. Y. Xu and Z. Ding reviewed the manuscript. Acknowledgements Not applicable. Data Availability All data generated or analysed during this study are included in this publishedarticle and its supplementary information files. References Matthay KK, Maris JM, Schleiermacher G, et al. Neuroblastoma[J] Nat Rev Dis Primers. 2016;2:16078. 10.1038/nrdp.2016.78 . Samim A, Tytgat GAM, Bleeker G, et al. Nuclear Medicine Imaging in Neuroblastoma: Current Status and New Developments[J]. J Personalized Med. 2021;11(4):270. 10.3390/jpm11040270 . Brisse HervéJ, Mccarville MB, Granata C, et al. Guidelines for Imaging and Staging of Neuroblastic Tumors: Consensus Report from the International Neuroblastoma. Risk Group Project[J] Radiol. 2011;261(1):243. 10.1148/radiol.11101352 . Huang M, Weiss WA. Neuroblastoma and MYCN, Cold Spring Harb. Perspect.Med. 3 (10) (2013), a014415. https://doi.org/10.1101/cshperspect.a014415 Bansal M, Gupta A, Ding HF. MYCN and Metabolic Reprogramming in Neuroblastoma. Cancers (Basel). 2022;14(17):4113. 10.3390/cancers14174113 . Won LJ, Hi SM, Won CH, et al. Clinical significance of MYCN amplification in patients with high-risk neuroblastoma[J]. Pediatr Blood Cancer. 2018;65:e27257. 10.1002/pbc.27257 . Kang SY, Rahim MK, Kim YI, et al. Clinical Significance of Pretreatment FDG PET/CT in MIBG-Avid Pediatric Neuroblastoma[J]. Nuclear Med Mol Imaging. 2017;51(2):1–7. 10.1007/s13139-016-0451-8 . Pfluger T, Piccardo A, Neuroblastoma. MIBG Imaging and New Tracers[J]. Semin Nucl Med. 2017;47(2):143. 10.1053/j.semnuclmed.2016.10.007 . Sharp SE, Trout AT, Weiss BD et al. MIBG in Neuroblastoma Diagnostic Imaging and Therapy. Radiographics. 2016 Jan-Feb;36(1):258–78. 10.1148/rg.2016150099 Brink A, Hlongwa KN, More S. The Impact of PET/CT on Paediatric Oncology. Diagnostics (Basel). 2023;13(2):192. 10.3390/diagnostics13020192 . Baratto L, Hawk KE, States L et al. PET/MRI Improves Management of Children with Cancer.[J].Society of Nuclear Medicine, 2021(10). 10.2967/JNUMED.120.259747 Monclair T, Brodeur GM, Ambros PF, et al. The International Neuroblastoma Risk Group (INRG) classification system: an INRG Task Force report.[J]. J Clin Oncol. 2009;27(2):289–97. 10.1200/JCO.2008.16.6785 . Ambros PF, Ambros IM, Brodeur GM et al. International consensus for neuroblastoma molecular diagnostics: report from the International Neuroblastoma Risk Group (INRG) Biology Committee.[J].The. Br J Cancer, 2009(9):100. 10.1038/sj.bjc.6605014 Shimada H, Ambros IM, Dehner LP, et al. Terminology and morphologic criteria of neuroblastic tumors: recommendations by the International Neuroblastoma Pathology Committee. Cancer. 1999;86(2):349–63. PMID: 10421272. Shimada H, Ambros IM, Dehner LP, et al. The International Neuroblastoma Pathology Classification (the Shimada system). Cancer. 1999;86(2):364–72. PMID: 10421273. Qian L, Yang S, Zhang S, et al. Prediction of MYCN Amplification, 1p and 11q Aberrations in Pediatric Neuroblastoma via Pre-therapy 18F-FDG PET/CT Radiomics. Front Med (Lausanne). 2022;9:840777. 10.3389/fmed.2022.840777 . Newman EA, Abdessalam S, Aldrink JH, et al. Update on neuroblastoma. J Pediatr Surg. 2019;54(3):383–9. 10.1016/j.jpedsurg.2018.09.004 . Feng L, Zhang S, Lu X, et al. An Optimal Radiomics Nomogram Based on 18 F-FDG PET/CT for Identifying Event-Free Survival in Pediatric Neuroblastoma. Acad Radiol. 2023;30(10):2309–20. 10.1016/j.acra.2023.06.004 . Li S, Liu J, Wang G, et al. Predictive value of 2-deoxy-2-fluorine-18-fluoro-D-glucose positron emission tomography/computed tomography parameters for MYCN amplification in high-risk neuroblastoma. Eur J Radiol. 2024;170:111243. 10.1016/j.ejrad.2023.111243 . Qian LD, Zhang SX, Li SQ, et al. Predicting MYCN amplification in paediatric neuroblastoma: development and validation of a 18F-FDG PET/CT-based radiomics signature. Insights Imaging. 2023;14(1):205. 10.1186/s13244-023-01493-8 . Pinto N, Naranjo A, Ding X, et al. Impact of Genomic and Clinical Factors on Outcome of Children ≥ 18 Months of Age with Stage 3 Neuroblastoma with Unfavorable Histology and without MYCN Amplification: A Children's Oncology Group (COG) Report. Clin Cancer Res. 2023;29(8):1546–56. 10.1158/1078-0432.CCR-22-3032 . Wang H, Wang X, Xu L, et al. Age related gene DST represents an independent prognostic factor for MYCN non-amplified neuroblastoma. BMC Pediatr. 2021;21(1):272. 10.1186/s12887-021-02753-6 . Bagatell R, Park JR, Acharya S, Neuroblastoma, et al. Version 2.2024, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Canc Netw. 2024;22(6):413–33. 10.6004/jnccn.2024.0040 . Li S, Liu J, Wang G et al. 18 F-FDG PET/CT volumetric parameter predicts prognosis for neuroblastoma with MYCN gain[J].Abdominal Radiology, 2025, 50(11):5614–27. 10.1007/s00261-025-04973-1 Boellaard R, Delgado-Bolton R, Oyen WJ, et al. European Association of Nuclear Medicine (EANM). FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015;42(2):328–54. 10.1007/s00259-014-2961-x . Pouliou M, Koutsi MA, Champezou L, et al. MYCN Amplifications and Metabolic Rewiring in Neuroblastoma. Cancers (Basel). 2023;15(19):4803. 10.3390/cancers15194803 . Hu R, Zhang Y, Liu S, et al. Prognostic prediction by 18F-FDG-PET/CT parameters in patients with neuroblastoma: a systematic review and meta-analysis. Front Oncol. 2023;13:1208531. 10.3389/fonc.2023.1208531 . Chaika M, Männlin S, Gassenmaier S, et al. Combined Metabolic and Functional Tumor Volumes on [18F]FDG-PET/MRI in Neuroblastoma Using Voxel-Wise Analysis. J Clin Med. 2023;12(18):5976. 10.3390/jcm12185976 . Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine.[J]. Nat Reviews Clin Oncol. 2017. 10.1038/nrclinonc.2017.141 . Feng L, Zhang S, Lu X et al. An Optimal Radiomics Nomogram Based on 18F-FDG PET/CT for Identifying Event-Free Survival in Pediatric Neuroblastoma[J].Academic radiology, 2023, 30(10):2309–20. 10.1016/j.acra.2023.06.004 Vickers AJ, Calster BV, Steyerberg. E W. A simple, step-by-step guide to interpreting decision curve analysis[J].Diagnostic and Prognostic Research, 2019, 3. 10.1186/s41512-019-0064-7 Rogers W, Thulasi Seetha S, Refaee TAG, et al. Radiomics: from qualitative to quantitative imaging. Br J Radiol. 2020;93(1108):20190948. 10.1259/bjr.20190948 . Thrall JH, Li X, Li Q, et al. Artificial Intelligence and Machine Learning in Radiology: Opportunities, Challenges, Pitfalls, and Criteria for Success[J]. J Am Coll Radiol. 2018;15(3):504–8. 10.1016/j.jacr.2017.12.026 . Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 05 Mar, 2026 Reviews received at journal 05 Mar, 2026 Reviews received at journal 19 Feb, 2026 Reviewers agreed at journal 15 Feb, 2026 Reviewers agreed at journal 12 Feb, 2026 Reviewers invited by journal 10 Feb, 2026 Editor invited by journal 04 Feb, 2026 Editor assigned by journal 04 Dec, 2025 Submission checks completed at journal 04 Dec, 2025 First submitted to journal 02 Dec, 2025 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-8265732","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":591626174,"identity":"db095447-4080-4424-ab56-6f61e60b7371","order_by":0,"name":"Jiangtao Liang","email":"","orcid":"","institution":"Hangzhou Universal Medical Imaging Diagnostic Center","correspondingAuthor":false,"prefix":"","firstName":"Jiangtao","middleName":"","lastName":"Liang","suffix":""},{"id":591626175,"identity":"334b211c-b33d-46bc-9f9b-f346d26c43e8","order_by":1,"name":"Feng Li","email":"","orcid":"","institution":"Hangzhou Universal Medical Imaging Diagnostic Center","correspondingAuthor":false,"prefix":"","firstName":"Feng","middleName":"","lastName":"Li","suffix":""},{"id":591626176,"identity":"143c1477-6b27-42df-85f9-9013841bfeeb","order_by":2,"name":"Zhongxiang Ding","email":"","orcid":"","institution":"Westlake University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Zhongxiang","middleName":"","lastName":"Ding","suffix":""},{"id":591626177,"identity":"bab5c61c-3725-4c11-b7e6-3cac2de01314","order_by":3,"name":"Bing Yan","email":"","orcid":"","institution":"Shanghai Universal Medical Imaging Diagnostic Center","correspondingAuthor":false,"prefix":"","firstName":"Bing","middleName":"","lastName":"Yan","suffix":""},{"id":591626178,"identity":"e3dc0685-c9d8-471c-a024-f9594f4bebe6","order_by":4,"name":"Yanfang Zhu","email":"","orcid":"","institution":"Hangzhou Universal Medical Imaging Diagnostic Center","correspondingAuthor":false,"prefix":"","firstName":"Yanfang","middleName":"","lastName":"Zhu","suffix":""},{"id":591626179,"identity":"183e64e8-1609-4583-bf66-1fbfd27c2596","order_by":5,"name":"Fangxiao Wang","email":"","orcid":"","institution":"Hangzhou Universal Medical Imaging Diagnostic Center","correspondingAuthor":false,"prefix":"","firstName":"Fangxiao","middleName":"","lastName":"Wang","suffix":""},{"id":591626180,"identity":"41c7a581-f973-4998-a6ef-5632375783c4","order_by":6,"name":"Yuanfan Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAw0lEQVRIiWNgGAWjYLCCChDB3tj48APRWs6ACJ7DzcYSpGmRSG8T4CFGtcGN5GcPDtTcSdxw82EbgwSDnZxuA0EtaeYGB449Mza4ndj2oIAh2djsAEEtCWbSH9gOywG1tBtIMBxI3EZYS/o3iQP/DvMY3DzYJsFDnJYcM4mDbUBbbjASqUXyzJsyiYN9h40lzyQCA9mACL/wHU/fJnHg2+HEvuPHHz78UGEnR1CLAqoCAwLKQUC+gQhFo2AUjIJRMMIBAG2gSvBGMCy0AAAAAElFTkSuQmCC","orcid":"","institution":"Hangzhou Universal Medical Imaging Diagnostic Center","correspondingAuthor":true,"prefix":"","firstName":"Yuanfan","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2025-12-03 04:23:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8265732/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8265732/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102962454,"identity":"42a47dee-b7de-43a8-9fff-504e4e671a24","added_by":"auto","created_at":"2026-02-19 04:08:54","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":94915,"visible":true,"origin":"","legend":"\u003cp\u003eForest plot of multivariate logistic regression analysis based on clinical and quantitative features.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8265732/v1/aca78f262fe3e2496e5788ea.png"},{"id":102962750,"identity":"62cac773-d555-46af-81bc-f69789f8fa67","added_by":"auto","created_at":"2026-02-19 04:10:56","extension":"jpeg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":49607,"visible":true,"origin":"","legend":"\u003cp\u003eROC curves and DCA for the four models. (A) ROC curve comparison. (B) DCA comparison; x-axis represents probability threshold, y-axis represents net benefit.\u003c/p\u003e","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8265732/v1/34dca906c81d9dc463188ff0.jpeg"},{"id":102757767,"identity":"2f8726ed-35c7-4ce6-a61e-88735cb3e515","added_by":"auto","created_at":"2026-02-16 10:04:33","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":179362,"visible":true,"origin":"","legend":"\u003cp\u003eCalibration curves for the four models. X-axis represents the predicted probability of MYCN amplification, Y-axis represents the actual probability of MYCN amplification.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8265732/v1/156501bb587f598959f82d89.png"},{"id":102757764,"identity":"c1f3516b-cc46-41ac-b40e-8912e228f5d3","added_by":"auto","created_at":"2026-02-16 10:04:33","extension":"jpeg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":56298,"visible":true,"origin":"","legend":"\u003cp\u003eThe nomogram for the combined model.\u003c/p\u003e","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8265732/v1/b74a7b0b60fb5e309ddbdce4.jpeg"},{"id":103049378,"identity":"4035dcba-45a0-4a07-ad3a-85132f0ab1dc","added_by":"auto","created_at":"2026-02-20 07:40:29","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1181009,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8265732/v1/29069dd8-5746-43cd-9184-f7d41ba7e1e3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Predictive Value of 18 F-FDG PET/MRI Parameters for MYCN Amplification in High-Risk Neuroblastoma","fulltext":[{"header":"Introduction","content":"\u003cp\u003eNeuroblastoma (NB), originating from neural crest cells, is the most common extracranial solid tumor in children [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. NB can arise anywhere along the sympathetic nervous chain, including the neck, chest, abdomen, pelvis, and other regions [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. However, the adrenal glands are the most common primary site, while locations like the neck and pelvis are relatively less frequent [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eNB is characterized by high malignancy and marked heterogeneity. Amplification of the MYCN proto-oncogene is a well-established independent predictor of poor prognosis. Approximately 20%-30% of HR-NB patients harbor MYCN amplification [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e], often presenting with rapid tumor progression, widespread metastases, and resistance to conventional chemotherapy and radiotherapy [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Identifying patients with poor prognosis at diagnosis is crucial for timely intervention to improve outcomes and survival. MYCN amplification status is not only a key indicator for risk stratification but also essential for designing targeted therapy strategies [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eHowever, current detection methods (e.g., fluorescence in situ hybridization and gene sequencing) rely on invasive tissue biopsies and cannot dynamically monitor changes in gene status, limiting their widespread clinical application. \u003csup\u003e123\u003c/sup\u003eI-metaiodobenzylguanidine (mIBG) scintigraphy is a well-established standard imaging modality for NB, with sensitivity and specificity both exceeding 90% [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Nevertheless, the lack of regulatory approval for \u003csup\u003e123\u003c/sup\u003eI in China hinders the widespread use of pre-treatment \u003csup\u003e123\u003c/sup\u003eI-mIBG scintigraphy for NB diagnosis [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. According to guidelines for \u003csup\u003e123\u003c/sup\u003eI-MIBG scintigraphy and staging [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e], \u003csup\u003e18\u003c/sup\u003eF-FDG PET/MRI serves as a complementary imaging technique, providing non-invasive information on tumor metabolism and microstructure, showcasing unique advantages in assessing tumor heterogeneity. Preliminary studies suggest that MYCN-amplified neuroblastomas exhibit higher glucose metabolic activity and specific diffusion characteristics, such as lower Apparent Diffusion Coefficient (ADC) values correlating with tumor cellularity and proliferative activity. However, current research predominantly focuses on PET/CT [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e] or single MRI parameters, lacking systematic exploration of combined PET/MRI multi-parameter models. Furthermore, physiological uptake in pediatric tumors (e.g., bone marrow, thymus) and the complexity of imaging-genomic correlations remain major challenges for accurate prediction.\u003c/p\u003e \u003cp\u003eThis study moves beyond the limitations of single imaging modalities by integrating \u003csup\u003e18\u003c/sup\u003eF-FDG PET/MRI parameters with clinical data to construct a multi-modal imaging model for the non-invasive prediction of MYCN amplification status in HR-NB patients. This model holds promise as a non-invasive imaging biomarker alternative to invasive biopsy, potentially providing a new tool for dynamic monitoring of MYCN status and treatment response assessment [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], thereby offering important theoretical support for precise risk stratification and optimization of targeted therapy strategies in HR-NB.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eResearch subjects\u003c/h2\u003e \u003cp\u003eWe retrospectively analyzed clinical data and PET/MRI images of 72 pediatric HR-NB patients treated at our institution between December 2018 and December 2024. Patients were classified according to the International Neuroblastoma Risk Group (INRG) classification system [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. All children underwent complete PET/MRI examination before any treatment and were diagnosed with HR-NB confirmed by histopathology and genetic testing. Inclusion criteria were: pathologically confirmed neuroblastoma; newly diagnosed lesion without prior anti-tumor therapy; availability of clear pre-treatment whole-body PET/MRI images; PET/MR examination performed 40\u0026ndash;60 minutes after radiopharmaceutical injection. Exclusion criteria were: PET or MRI images not meeting diagnostic standards (e.g., metal or motion artifacts); suspected inaccuracies in SUV values; patients with other concurrent systemic malignancies; patients who have received any form of treatment (such as radiotherapy, chemotherapy, etc.) before undergoing PET/MR examination. Collected imaging data included: Necrosis, Calcification, Hemorrhage, Mean diameter, Maximum Standardized Uptake Value (SUVmax), Mean Standardized Uptake Value (SUVmean), Peak Standardized Uptake Value (SUVpeak), Metabolic Tumor Volume (MTV), Total Lesion Glycolysis (TLG), Mean Apparent Diffusion Coefficient (ADCmean), Coefficient of Variation (COV), and Image-Defined Risk Factors (IDRFs). Provided clinical data included age, sex, primary tumor site, histology, and INRG stage. The International Neuroblastoma Risk Group Staging System (INRGSS) [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] and the International Neuroblastoma Pathology Classification [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e] were used for staging and histologic classification, respectively. Based on MYCN amplification status, patients were divided into MYCN-amplified (MNA) and non-amplified (MYCN-NA) groups. Data collection was approved by the hospital's Medical Ethics Committee (Approval No: medical ethics [2025]008), with informed consent obtained from guardians. All procedures followed the principles of the Declaration of Helsinki.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eInstrumentation\u003c/h3\u003e\n\u003cp\u003eImaging data were acquired using a United States GE Healthcare integrated Time-of-Flight(TOF) PET/MRI system (GE SIGNA, Wisconsin, USA). This system consists of a PET detector equipped with time - of - flight (TOF) technology (TOF - PET) and the latest - generation 750W 3.0T MRI device. The TOF-PET detector utilizes advanced solid-state silicon photomultipliers (SiPMs) and the latest LBS crystals. The radiopharmaceutical used was \u003csup\u003e18\u003c/sup\u003eF-fludeoxyglucose(\u003csup\u003e18\u003c/sup\u003eF-FDG).\u003c/p\u003e\n\u003ch3\u003eData Analysis and Measurement\u003c/h3\u003e\n\u003cp\u003eAll images were interpreted by three radiologists who possess more than a decade of experience in the diagnosis of pediatric tumors and hold certifications in MRI and nuclear medicine. They reached a consensus through discussion. The PET VCAR software within the GE Healthcare AW 4.6 post - processing workstation was utilized to measure various quantitative parameters. For image analysis, both visual analysis and semi - quantitative analysis methods were primarily adopted. Conventional semi-quantitative metabolic parameters obtained included SUVmax, SUVmean, SUVpeak, MTV, TLG, ADCmean, and COV, where ADCmean was the average of ADC values from three points within the solid tumor component, and COV = (Standard deviation of SUV / SUVmean) \u0026times; 100.\u003c/p\u003e\n\u003ch3\u003eMYCN Status Detection\u003c/h3\u003e\n\u003cp\u003eMYCN status was determined using Fluorescence In Situ Hybridization (FISH) on formalin-fixed, paraffin-embedded samples obtained via biopsy or surgical resection. According to international consensus for molecular diagnostics in neuroblastoma, a target gene copy number equal to the chromosome 2 copy number was defined as negative (\u0026le;\u0026thinsp;2); 3\u0026ndash;9 copies as gain; and \u0026ge;\u0026thinsp;10 copies (\u0026ge;\u0026thinsp;5 times the chromosome 2 count) as amplified [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eStatistical Analysis\u003c/h2\u003e \u003cp\u003eData processing and statistical analysis were performed using SPSS software V23.0 and R software V4.2.3. The Shapiro-Wilk test assessed normality. Normally distributed data are expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation and analyzed using the t-test. Non-normally distributed data are expressed as median (Q1, Q3) and analyzed using the Mann-Whitney U test. Categorical data were compared using the chi-square test or Fisher's exact test. Multivariate logistic regression analysis was used to select independent predictors. ROC curves assessed the diagnostic performance of individual predictors and the combined model for predicting risk, calculating the AUC, sensitivity, and specificity. Calibration plots and Decision Curve Analysis (DCA) determined the calibration and clinical utility of the models, respectively. The DeLong test compared the diagnostic performance of the models, with P\u0026thinsp;\u0026lt;\u0026thinsp;0.05 considered statistically significant. The combined model was visualized using a nomogram.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eReproducibility Assessment\u003c/h2\u003e \u003cp\u003eThree doctors conducted a consistency check on the qualitative features. As quantitative features were automatically extracted by the GE workstation, no consistency check was needed for them. The Kappa value was used as a measure of inter-observer consistency, with a Kappa value\u0026thinsp;\u0026ge;\u0026thinsp;0.75 indicating good consistency.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003eClinical Characteristics\u003c/h2\u003e \u003cp\u003eClinical characteristics of all patients are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. The cohort comprised 72 patients, including 44 males and 28 females. Among them, 29 patients had MYCN amplification (MNA) group, while the remaining 43 were non-amplified (MYCN-NA) group. The mean ages were 37 months and 52 months, respectively, with the non-amplified group being significantly older (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Most tumors were located in the adrenal glands (n\u0026thinsp;=\u0026thinsp;49), with a smaller proportion observed in other regions (n\u0026thinsp;=\u0026thinsp;23). The majority of patients (n\u0026thinsp;=\u0026thinsp;58, 80.6%) had IDRFs present, while a minority (n\u0026thinsp;=\u0026thinsp;14, 19.4%) did not. According to INRGSS, in the MYCN-NA group, 3 (7%) were stage L1, 8 (19%) were stage L2, and 32 (74%) were stage M. Conversely, in the MNA group, 2 (7%) were stage L2, and 27 (93%) were stage M. No significant differences were found between the amplified and non-amplified groups regarding Gender, Primary site, IDRFs, or Stage.\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\u003eClinical characteristics between the MYCN amplification group (MNA) and the non-amplification group (MYCN-NA).\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\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=\"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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMNA(n\u0026thinsp;=\u0026thinsp;29)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMYCN-NA(n\u0026thinsp;=\u0026thinsp;43)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e统计量\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eP值\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge(month)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e37(8\u0026ndash;96)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52(20\u0026ndash;108)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026minus;3.048\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGender(n, %)\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=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.125\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.724\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e17(59%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e27(63%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12(41%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16(37%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePrimary site(n, %)\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=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.746\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.382\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdrenal gland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21(72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e28(68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOther\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7(28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16(32%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIDRFs (n, %)\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=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.803\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.370\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epositive\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21(72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37(84%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003enegative\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7(28%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7(16%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStage (n, %)\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=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4.471\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.107\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eL1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0(0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3(7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eL2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2(7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8(19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e27(93%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32(74%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0(0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0(0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eIDRFs, Image-Defined Risk Factors.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eMultivariate Logistic Regression Analysis Combining Qualitative and Quantitative Features\u003c/h2\u003e \u003cp\u003eResults of the multivariate analysis incorporating clinical and quantitative features are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The analysis indicated that Thanatosis (P\u0026thinsp;=\u0026thinsp;0.039, OR\u0026thinsp;=\u0026thinsp;5.520, 95% CI: 1.091\u0026ndash;27.916), Age (P\u0026thinsp;=\u0026thinsp;0.042; OR\u0026thinsp;=\u0026thinsp;0.959, 95% CI: 0.920\u0026ndash;0.999), and TLG (P\u0026thinsp;=\u0026thinsp;0.011; OR\u0026thinsp;=\u0026thinsp;1.004, 95% CI: 0.982\u0026ndash;1.008) were confirmed as independent predictors for the amplification group.The multivariate logistic analysis is depicted in a forest plot (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\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\u003eMultivariate logistic regression analysis for the association between significant indices and MYCN amplification.\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=\"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=\"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\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eMNA\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eMYCN-NA\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e统计量\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cem\u003eP value\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e \u003cp\u003eUnivariate analysis\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOR(95%CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003e\u003cem\u003eP value\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThanatosis\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=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e7.473\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.006\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e5.520(1.091\u0026ndash;27.916)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.039\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\u003e19(65.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14(32.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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\u003eNO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10(34.5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e29(67.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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\u003eCalcification\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=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4.416\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.036\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.374(0.068\u0026ndash;2.071)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.260\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\u003e17(58.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e35(81.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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\u003eNO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12(41.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8(18.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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\u003eHemorrhage\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=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3.284\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.070\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.961(0.403\u0026ndash;9.542)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.404\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\u003e11(37.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8(18.6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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\u003eNO\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18(62.1%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e35(81.4%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\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\u003eAge(month)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e24(17,48)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48(36, 6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3.269\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.959(0.920\u0026ndash;0.999)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.042\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMean diameter(cm)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.81\u0026thinsp;\u0026plusmn;\u0026thinsp;2.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.08\u0026thinsp;\u0026plusmn;\u0026thinsp;3.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.030\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.307\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.825(0.549\u0026ndash;1.237)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.352\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSUV \u003csub\u003emax\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.63\u0026thinsp;\u0026plusmn;\u0026thinsp;2.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.39\u0026thinsp;\u0026plusmn;\u0026thinsp;398\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.275\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.784\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.705(0.365\u0026ndash;1.364)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.299\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSUV \u003csub\u003emean\u003c/sub\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.46(3.17,5.06)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.65(2.76, 4.92)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.987\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.323\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.226(0.388\u0026ndash;3.872\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.729\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMTV(cm\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e179.00(52.35, 314.50)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e67.68(25.60, 155.00)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.543\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.051\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.997(0.987\u0026ndash;1.009)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.712\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTLG(g)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e620.00(211.50, 1543.60)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e223.80(67.70,440.80)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3.008\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.003\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1.004(0.982\u0026ndash;1.008)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.011\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eADCmean(\u0026times;10⁻\u0026sup3;mm\u0026sup2;/s)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.71(0.63, 0.83)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.68(0.60, 0.78)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e-0.706\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e2.446(0.035\u0026ndash;169.60)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.679\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCOV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e18.24\u0026thinsp;\u0026plusmn;\u0026thinsp;2.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e18.98\u0026thinsp;\u0026plusmn;\u0026thinsp;2.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e-1.156\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.252\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.957(0.746\u0026ndash;1.227)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e \u003cp\u003e0.727\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eSUVmax, maximum standardized uptake value; SUVmean, mean standardized uptake value; MTV, tumor metabolic volume; TLG, total lesion glycolysis; ADCmean, mean Apparent Diffusion Coefficient; COV, coefficient of variation.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003ePredictive Performance Evaluation of the Models\u003c/h2\u003e \u003cp\u003eThe Youden Index from ROC analysis indicated optimal cut-off values of 24 months for Age and 479.7 for TLG. ROC curve analysis showed that the independent predictor TLG exhibited the highest predictive performance among individual parameters (AUC: 0.791, 95% CI: 0.679\u0026ndash;0.878, Sensitivity: 0.724, Specificity: 0.837). Similarly, Age showed high predictive accuracy among clinical parameters (AUC: 0.724, 95% CI: 0.606\u0026ndash;0.823, Sensitivity: 0.517, Specificity: 0.930). Tumor Necrosis was another independent predictor (AUC: 0.648, 95% CI: 0.526\u0026ndash;0.757, Sensitivity: 0.621, Specificity: 0.674). The predictive model constructed by combining these three independent predictors showed improved diagnostic efficacy compared to using Necrosis, Age, or TLG alone, with an AUC of 0.858 (95% CI: 0.756\u0026ndash;0.929, Sensitivity: 0.724, Specificity: 0.930) (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The DCA curves for the four models (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e) indicated that the combined model had the best clinical utility. The four models were evaluated using calibration curves (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The nomogram for the combined model is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\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\u003eDiscriminative diagnostic efficiency of significant parameters between MYCN amplified and non-amplified groups.\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\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCut-off\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003cp\u003e(95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSensitivity\u003c/p\u003e \u003cp\u003e(95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSpecificity\u003c/p\u003e \u003cp\u003e(95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eP-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThanatosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.648(0.526\u0026ndash;0.757)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.621(0.423\u0026ndash;0.793)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.674(0.515\u0026ndash;0.809)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e0.011\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge(month)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.724(0.606\u0026ndash;0.823)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.517(0.325\u0026ndash;0.706)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.930(0.809\u0026ndash;0.985)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTLG\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e479.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.791(0.679\u0026ndash;0.878)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.724(0.528\u0026ndash;0.873)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.837(0.693\u0026ndash;0.932)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCombined model\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.858(0.756\u0026ndash;0.929)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.724(0.528\u0026ndash;0.873)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.930(0.809\u0026ndash;0.985)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e\u0026lt;0.001\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 \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eReproducibility Assessment\u003c/h2\u003e \u003cp\u003eThe consistency check for qualitative features is shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, indicating good inter-observer agreement, with Kappa values ranging from 0.762 to 0.806.\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\u003eConsistency check results for qualitative features.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eN (% of concordance)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eKappa (95% CI)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eP value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThanatosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e65/72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.806(0.669\u0026ndash;0.943)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCalcification\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e62/72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.762(0.562\u0026ndash;0.882)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemorrhage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e64/72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.778(0.633\u0026ndash;0.925)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;0.001\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"},{"header":"Discussion","content":"\u003cp\u003eNeuroblastoma (NB) is an embryonic tumor arising from neural crest cells, with malignant transformation possible at any stage of differentiation. NB is highly heterogeneous; some NB cells may grow slowly yet be highly malignant, while others grow rapidly but can spontaneously differentiate into benign forms or even regress [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. MYCN amplification is a major driver of oncogenesis in NB, occurring in approximately 30%-40% of HR-NB patients and playing a crucial role in its initiation and early development [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. This study is the first to elucidate the role of clinical characteristics and \u003csup\u003e18\u003c/sup\u003eF-FDG PET/MR imaging parameters in predicting MYCN amplification in HR-NB patients. Our findings indicate that MYCN amplification occurred in 40% of HR-NB patients, consistent with previous reports [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. The results demonstrate that clinical features and metabolic parameters derived from \u003csup\u003e18\u003c/sup\u003eF-FDG PET/MR can effectively distinguish between MYCN-amplified and non-amplified HR-NB, with tumor necrosis, age, and TLG identified as independent predictors of MYCN amplification. Furthermore, we constructed a predictive model based on these three factors, which significantly enhanced the ability to discriminate MYCN amplification status.\u003c/p\u003e \u003cp\u003eThe significant association between tumor necrosis and MYCN amplification (OR\u0026thinsp;=\u0026thinsp;5.52, P\u0026thinsp;=\u0026thinsp;0.039) aligns with previous research linking necrotic areas to hypoxia-driven genomic instability and chemotherapy resistance in MYCN-amplified tumors [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. Tumor necrosis reflects tumor proliferation outpacing its blood supply, a characteristic driven by MYCN oncogene activity [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. In neuroblastoma, radiomics analyses have also identified necrotic patterns as predictors of poor prognosis, although their standalone predictive accuracy remains moderate (AUC: 0.648) [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. The low sensitivity (62.1%) and specificity (67.4%) of necrosis alone for predicting MYCN amplification highlight the necessity of integrating metabolic parameters and clinical data for comprehensive risk assessment.\u003c/p\u003e \u003cp\u003eAge was a risk factor for MYCN amplification (OR\u0026thinsp;=\u0026thinsp;0.959, P\u0026thinsp;=\u0026thinsp;0.042), consistent with epidemiological trends showing a peak incidence of MYCN amplification in children over 18 months [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Older age in neuroblastoma patients is generally associated with poorer outcomes compared to younger patients. However, research on age specifically for predicting MYCN amplification is limited [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Our study showed that age had high specificity (93.0%) but low sensitivity (51.7%) for predicting MYCN amplification, underscoring the need for multi-modal models to compensate for the limitations of using age alone [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. This aligns with recent consensus guidelines in pediatric oncology advocating for combined clinical and imaging models [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eTotal Lesion Glycolysis (TLG), reflecting both glycolytic activity and tumor burden, exhibited the strongest individual predictive performance (AUC: 0.791). MYCN amplification is known to upregulate glucose metabolism via GLUT1 overexpression and hexokinase activation [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e], and TLG quantifies this more comprehensively than static indices like SUVmax [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Our findings are consistent with Li et al. [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e], who identified TLG as a key discriminator of MYCN status in HR-NB. However, the wide confidence interval for TLG's OR (95% CI: 0.982\u0026ndash;1.008) suggests metabolic heterogeneity, emphasizing the need for supplemental biomarkers.\u003c/p\u003e \u003cp\u003eThe combined model incorporating tumor necrosis, age, and TLG achieved higher diagnostic accuracy (AUC: 0.858), outperforming individual parameters. This synergistic effect is analogous to advances in radiomics, where hybrid models integrating imaging and clinical data improve prognostic accuracy in radiogenomics [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. For instance, Feng et al. [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e] developed a PET/CT-based nomogram combining radiomic features with INRG stage, achieving comparable predictive ability (AUC: 0.840). Our calibration curves and DCA further validate the clinical utility of such models, offering a non-invasive alternative to biopsy for MYCN risk stratification [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eDespite the positive results, this study has several limitations. First, the relatively small sample size may limit the generalizability of the model [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. Second, the single-center design potentially introduces selection bias. Future studies are needed to validate this model in larger, multi-center patient cohorts. Future research should focus on: (1) validating the model's predictive power in larger patient populations; (2) exploring its applicability across different age and ethnic groups; (3) further optimizing the risk assessment model by incorporating radiomics data [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. The future goal is to utilize large-sample, multi-center cohort studies to evaluate its value in distinguishing risk within INRGSS high-risk and non-high-risk groups.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, the model based on qualitative and quantitative features from \u003csup\u003e18\u003c/sup\u003eF-FDG PET/MRI provides a novel method for differentiating MYCN amplification status in neuroblastoma patients. Compared to existing literature, this approach offers a more comprehensive and precise analysis of tumor characteristics and holds promise for widespread clinical application.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e \u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e \u003cp\u003eData collection was approved by the hospital's Medical Ethics Committee (Approval No: medical ethics [2025]008), with informed consent obtained from guardians. All procedures followed the principles of the Declaration of Helsinki.\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 \u003cstrong\u003eCompeting interests\u003c/strong\u003e \u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e \u003c/p\u003e\u003cp\u003e \u003ch2\u003eAuthor details\u003c/h2\u003e \u003cp\u003e \u003csup\u003e1\u003c/sup\u003eHangzhou Universal Medical Imaging Diagnostic Center, No. 893 Jiangcheng Rd., Hangzhou, Zhejiang, China\u003c/p\u003e \u003cp\u003e \u003csup\u003e2\u003c/sup\u003eShanghai Universal Medical Imaging Diagnostic Center, No.8 Building, Huaxin Center, 406 Guilin Road, Xuhui District, Shanghai, China\u003c/p\u003e \u003cp\u003e \u003csup\u003e3\u003c/sup\u003eDepartment of Radiology, Affiliated Hangzhou First People\u0026rsquo;s Hospital, Westlake University School of Medicine, Hangzhou, Zhejiang, China\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e \u003cp\u003eThis research is supported by Medical Science and Technology Project of Zhejiang Province(NO. 2022KY1047, 2024KY1428).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003e1. Liang and F. Li were responsible for the study design and wrote the main manuscript text. B. Yan, Y. Zhu and F. Wang conducted the data analysis. Y. Xu and Z. Ding reviewed the manuscript.\u003c/p\u003e\u003ch2\u003eAcknowledgements\u003c/h2\u003e \u003cp\u003eNot applicable.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eAll data generated or analysed during this study are included in this publishedarticle and its supplementary information files.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eMatthay KK, Maris JM, Schleiermacher G, et al. Neuroblastoma[J] Nat Rev Dis Primers. 2016;2:16078. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/nrdp.2016.78\u003c/span\u003e\u003cspan address=\"10.1038/nrdp.2016.78\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSamim A, Tytgat GAM, Bleeker G, et al. Nuclear Medicine Imaging in Neuroblastoma: Current Status and New Developments[J]. J Personalized Med. 2021;11(4):270. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/jpm11040270\u003c/span\u003e\u003cspan address=\"10.3390/jpm11040270\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBrisse Herv\u0026eacute;J, Mccarville MB, Granata C, et al. Guidelines for Imaging and Staging of Neuroblastic Tumors: Consensus Report from the International Neuroblastoma. Risk Group Project[J] Radiol. 2011;261(1):243. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1148/radiol.11101352\u003c/span\u003e\u003cspan address=\"10.1148/radiol.11101352\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang M, Weiss WA. Neuroblastoma and MYCN, Cold Spring Harb. Perspect.Med. 3 (10) (2013), a014415. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1101/cshperspect.a014415\u003c/span\u003e\u003cspan address=\"10.1101/cshperspect.a014415\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBansal M, Gupta A, Ding HF. MYCN and Metabolic Reprogramming in Neuroblastoma. Cancers (Basel). 2022;14(17):4113. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cancers14174113\u003c/span\u003e\u003cspan address=\"10.3390/cancers14174113\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWon LJ, Hi SM, Won CH, et al. Clinical significance of MYCN amplification in patients with high-risk neuroblastoma[J]. Pediatr Blood Cancer. 2018;65:e27257. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/pbc.27257\u003c/span\u003e\u003cspan address=\"10.1002/pbc.27257\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKang SY, Rahim MK, Kim YI, et al. Clinical Significance of Pretreatment FDG PET/CT in MIBG-Avid Pediatric Neuroblastoma[J]. Nuclear Med Mol Imaging. 2017;51(2):1\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s13139-016-0451-8\u003c/span\u003e\u003cspan address=\"10.1007/s13139-016-0451-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePfluger T, Piccardo A, Neuroblastoma. MIBG Imaging and New Tracers[J]. Semin Nucl Med. 2017;47(2):143. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1053/j.semnuclmed.2016.10.007\u003c/span\u003e\u003cspan address=\"10.1053/j.semnuclmed.2016.10.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSharp SE, Trout AT, Weiss BD et al. MIBG in Neuroblastoma Diagnostic Imaging and Therapy. Radiographics. 2016 Jan-Feb;36(1):258\u0026ndash;78. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1148/rg.2016150099\u003c/span\u003e\u003cspan address=\"10.1148/rg.2016150099\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBrink A, Hlongwa KN, More S. The Impact of PET/CT on Paediatric Oncology. Diagnostics (Basel). 2023;13(2):192. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/diagnostics13020192\u003c/span\u003e\u003cspan address=\"10.3390/diagnostics13020192\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaratto L, Hawk KE, States L et al. PET/MRI Improves Management of Children with Cancer.[J].Society of Nuclear Medicine, 2021(10).\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2967/JNUMED.120.259747\u003c/span\u003e\u003cspan address=\"10.2967/JNUMED.120.259747\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMonclair T, Brodeur GM, Ambros PF, et al. The International Neuroblastoma Risk Group (INRG) classification system: an INRG Task Force report.[J]. J Clin Oncol. 2009;27(2):289\u0026ndash;97. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1200/JCO.2008.16.6785\u003c/span\u003e\u003cspan address=\"10.1200/JCO.2008.16.6785\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmbros PF, Ambros IM, Brodeur GM et al. International consensus for neuroblastoma molecular diagnostics: report from the International Neuroblastoma Risk Group (INRG) Biology Committee.[J].The. Br J Cancer, 2009(9):100.\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/sj.bjc.6605014\u003c/span\u003e\u003cspan address=\"10.1038/sj.bjc.6605014\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShimada H, Ambros IM, Dehner LP, et al. Terminology and morphologic criteria of neuroblastic tumors: recommendations by the International Neuroblastoma Pathology Committee. Cancer. 1999;86(2):349\u0026ndash;63. PMID: 10421272.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShimada H, Ambros IM, Dehner LP, et al. The International Neuroblastoma Pathology Classification (the Shimada system). Cancer. 1999;86(2):364\u0026ndash;72. PMID: 10421273.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQian L, Yang S, Zhang S, et al. Prediction of MYCN Amplification, 1p and 11q Aberrations in Pediatric Neuroblastoma via Pre-therapy 18F-FDG PET/CT Radiomics. Front Med (Lausanne). 2022;9:840777. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fmed.2022.840777\u003c/span\u003e\u003cspan address=\"10.3389/fmed.2022.840777\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNewman EA, Abdessalam S, Aldrink JH, et al. Update on neuroblastoma. J Pediatr Surg. 2019;54(3):383\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jpedsurg.2018.09.004\u003c/span\u003e\u003cspan address=\"10.1016/j.jpedsurg.2018.09.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFeng L, Zhang S, Lu X, et al. An Optimal Radiomics Nomogram Based on \u003csup\u003e18\u003c/sup\u003eF-FDG PET/CT for Identifying Event-Free Survival in Pediatric Neuroblastoma. Acad Radiol. 2023;30(10):2309\u0026ndash;20. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.acra.2023.06.004\u003c/span\u003e\u003cspan address=\"10.1016/j.acra.2023.06.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi S, Liu J, Wang G, et al. Predictive value of 2-deoxy-2-fluorine-18-fluoro-D-glucose positron emission tomography/computed tomography parameters for MYCN amplification in high-risk neuroblastoma. Eur J Radiol. 2024;170:111243. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.ejrad.2023.111243\u003c/span\u003e\u003cspan address=\"10.1016/j.ejrad.2023.111243\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQian LD, Zhang SX, Li SQ, et al. Predicting MYCN amplification in paediatric neuroblastoma: development and validation of a 18F-FDG PET/CT-based radiomics signature. Insights Imaging. 2023;14(1):205. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s13244-023-01493-8\u003c/span\u003e\u003cspan address=\"10.1186/s13244-023-01493-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePinto N, Naranjo A, Ding X, et al. Impact of Genomic and Clinical Factors on Outcome of Children\u0026thinsp;\u0026ge;\u0026thinsp;18 Months of Age with Stage 3 Neuroblastoma with Unfavorable Histology and without MYCN Amplification: A Children's Oncology Group (COG) Report. Clin Cancer Res. 2023;29(8):1546\u0026ndash;56. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1158/1078-0432.CCR-22-3032\u003c/span\u003e\u003cspan address=\"10.1158/1078-0432.CCR-22-3032\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang H, Wang X, Xu L, et al. Age related gene DST represents an independent prognostic factor for MYCN non-amplified neuroblastoma. BMC Pediatr. 2021;21(1):272. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12887-021-02753-6\u003c/span\u003e\u003cspan address=\"10.1186/s12887-021-02753-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBagatell R, Park JR, Acharya S, Neuroblastoma, et al. Version 2.2024, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Canc Netw. 2024;22(6):413\u0026ndash;33. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.6004/jnccn.2024.0040\u003c/span\u003e\u003cspan address=\"10.6004/jnccn.2024.0040\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi S, Liu J, Wang G et al. \u003csup\u003e18\u003c/sup\u003eF-FDG PET/CT volumetric parameter predicts prognosis for neuroblastoma with MYCN gain[J].Abdominal Radiology, 2025, 50(11):5614\u0026ndash;27.\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00261-025-04973-1\u003c/span\u003e\u003cspan address=\"10.1007/s00261-025-04973-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBoellaard R, Delgado-Bolton R, Oyen WJ, et al. European Association of Nuclear Medicine (EANM). FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015;42(2):328\u0026ndash;54. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s00259-014-2961-x\u003c/span\u003e\u003cspan address=\"10.1007/s00259-014-2961-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePouliou M, Koutsi MA, Champezou L, et al. MYCN Amplifications and Metabolic Rewiring in Neuroblastoma. Cancers (Basel). 2023;15(19):4803. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cancers15194803\u003c/span\u003e\u003cspan address=\"10.3390/cancers15194803\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu R, Zhang Y, Liu S, et al. Prognostic prediction by 18F-FDG-PET/CT parameters in patients with neuroblastoma: a systematic review and meta-analysis. Front Oncol. 2023;13:1208531. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fonc.2023.1208531\u003c/span\u003e\u003cspan address=\"10.3389/fonc.2023.1208531\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChaika M, M\u0026auml;nnlin S, Gassenmaier S, et al. Combined Metabolic and Functional Tumor Volumes on [18F]FDG-PET/MRI in Neuroblastoma Using Voxel-Wise Analysis. J Clin Med. 2023;12(18):5976. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/jcm12185976\u003c/span\u003e\u003cspan address=\"10.3390/jcm12185976\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine.[J]. Nat Reviews Clin Oncol. 2017. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/nrclinonc.2017.141\u003c/span\u003e\u003cspan address=\"10.1038/nrclinonc.2017.141\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFeng L, Zhang S, Lu X et al. An Optimal Radiomics Nomogram Based on 18F-FDG PET/CT for Identifying Event-Free Survival in Pediatric Neuroblastoma[J].Academic radiology, 2023, 30(10):2309\u0026ndash;20.\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.acra.2023.06.004\u003c/span\u003e\u003cspan address=\"10.1016/j.acra.2023.06.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVickers AJ, Calster BV, Steyerberg. E W. A simple, step-by-step guide to interpreting decision curve analysis[J].Diagnostic and Prognostic Research, 2019, 3.\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s41512-019-0064-7\u003c/span\u003e\u003cspan address=\"10.1186/s41512-019-0064-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRogers W, Thulasi Seetha S, Refaee TAG, et al. Radiomics: from qualitative to quantitative imaging. Br J Radiol. 2020;93(1108):20190948. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1259/bjr.20190948\u003c/span\u003e\u003cspan address=\"10.1259/bjr.20190948\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThrall JH, Li X, Li Q, et al. Artificial Intelligence and Machine Learning in Radiology: Opportunities, Challenges, Pitfalls, and Criteria for Success[J]. J Am Coll Radiol. 2018;15(3):504\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jacr.2017.12.026\u003c/span\u003e\u003cspan address=\"10.1016/j.jacr.2017.12.026\" 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-cancer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bcan","sideBox":"Learn more about [BMC Cancer](http://bmccancer.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bcan/default.aspx","title":"BMC Cancer","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"18F-FDG PET/MRI, Neuroblastoma, MYCN Amplification","lastPublishedDoi":"10.21203/rs.3.rs-8265732/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8265732/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eTo investigate the clinical value of \u003csup\u003e18\u003c/sup\u003eF-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging (\u003csup\u003e18\u003c/sup\u003eF-FDG PET/MRI) parameters in predicting the MYCN gene amplification status in patients with high-risk neuroblastoma (HR-NB).\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA retrospective analysis was conducted on 72 HR-NB patients who underwent \u003csup\u003e18\u003c/sup\u003eF-FDG PET/MRI examinations at our institution between December 2018 and December 2024. Based on MYCN genetic testing results, the patients were classified into the MYCN amplification group (MNA) and the non-amplification group (MYCN-NA). The clinical data of the patients and the imaging characteristics of the primary tumors were collected. The GE post-processing workstation was used to identify lesions, and quantitative parameters on PET/MRI images were semi-automatically extracted. Multivariable logistic regression analysis was employed to screen for independent predictive factors. Diagnostic performance was assessed using Receiver Operating Characteristic (ROC) curves by calculating the Area Under the Curve (AUC), sensitivity, and specificity. Calibration plot and Decision Curve Analysis (DCA) were used to evaluate the calibration and clinical utility of the models, respectively. A combined model was visualized using a nomogram.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eMultivariate logistic regression analysis identified tumor necrosis (P\u0026thinsp;=\u0026thinsp;0.039, OR\u0026thinsp;=\u0026thinsp;5.52; 95% CI: 1.091\u0026ndash;27.916), age (P\u0026thinsp;=\u0026thinsp;0.042, OR\u0026thinsp;=\u0026thinsp;0.959; 95% CI: 0.920\u0026ndash;0.999), and Total Lesion Glycolysis (TLG) (P\u0026thinsp;=\u0026thinsp;0.011, OR\u0026thinsp;=\u0026thinsp;1.004; 95% CI: 0.982\u0026ndash;1.008) as independent predictive factors of MYCN amplification in HR-NB. ROC curve analysis demonstrated that the diagnostic performance of the combined model had superior diagnostic performance (AUC: 0.858, 95% CI: 0.756\u0026ndash;0.929, Sensitivity: 0.724, Specificity: 0.930) compared to using necrosis alone (AUC: 0.648, 95% CI: 0.526\u0026ndash;0.757, Sensitivity: 0.621, Specificity: 0.674), age alone (AUC: 0.724, 95% CI: 0.606\u0026ndash;0.823, Sensitivity: 0.517, Specificity: 0.930), or TLG alone (AUC: 0.791, 95% CI: 0.679\u0026ndash;0.878, Sensitivity: 0.724, Specificity: 0.837). Calibration curves and DCA further confirmed the optimal clinical utility of the combined model.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe prediction model integrating tumor necrosis, TLG, and age can effectively and non-invasively predict the MYCN amplification status in HR-NB patients, exhibiting good diagnostic efficacy and clinical application potential.\u003c/p\u003e","manuscriptTitle":"Predictive Value of 18 F-FDG PET/MRI Parameters for MYCN Amplification in High-Risk Neuroblastoma","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-16 10:04:29","doi":"10.21203/rs.3.rs-8265732/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-05T18:13:52+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-05T11:45:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-19T09:08:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"193193970027949960540634730900261462425","date":"2026-02-15T12:29:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7404936394181416752924382528965464995","date":"2026-02-12T12:24:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-10T17:31:56+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-04T05:21:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-05T00:58:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-05T00:57:16+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Cancer","date":"2025-12-03T04:17:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-cancer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bcan","sideBox":"Learn more about [BMC Cancer](http://bmccancer.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bcan/default.aspx","title":"BMC Cancer","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0bb65d68-9c33-4b93-a79a-c802a4c5832b","owner":[],"postedDate":"February 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-03-05T18:24:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-16 10:04:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8265732","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8265732","identity":"rs-8265732","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}