Feasibility of Automated Accurate Lung Segmentation Using Deep Learning on Virtual Unenhanced Images from Gemstone Spectral CT Imaging For Pulmonary Ventilation Assessment

Feasibility of Automated Accurate Lung Segmentation Using Deep Learning on Virtual Unenhanced Images from Gemstone Spectral CT Imaging For Pulmonary Ventilation Assessment | 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 Feasibility of Automated Accurate Lung Segmentation Using Deep Learning on Virtual Unenhanced Images from Gemstone Spectral CT Imaging For Pulmonary Ventilation Assessment Chao Zou, Jun Hu, An Yan, Aiyun Sun, Wen Yang, Xin Peng, Xu Yang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7300980/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Objective : To evaluate the feasibility of applying deep learning-based automatic lung segmentation to virtual unenhanced (VUE) images generated from gemstone spectral imaging (GSI) CT scans. Materials and Methods : This retrospective study included patients who underwent chest CT scans. The protocol consisted of conventional true unenhanced (TUE) scans, arterial-phase (AP) GSI-enhanced scans, and venous-phase (VP) GSI-enhanced scans. VUE images were reconstructed from both enhanced phases. A deep neural network was utilized to automatically segment lung lobes and calculate total lung volume, weight and relative fractions, as well as the volume and weight fractions of regions with different ventilation functionality. Differences among the three image sets, as well as their correlations, bias, and mean absolute percentage error (MAPE), were assessed. Results : A total of 223 patients were enrolled. Statistically significant differences were observed between TUE and AP-VUE in the weight fractions of normally ventilated regions, and between TUE and both AP-VUE and VP-VUE in the weight fractions of poorly ventilated regions (all P 0.05). The correlation coefficients of non-ventilated region weight fractions between AP-VUE and TUE, and between VP-VUE and TUE, were 0.75 and 0.76, respectively; all other correlation coefficients exceeded 0.80. Bias values for lobar and functional region volume and weight fractions ranged from − 1.62 to 1.23, while MAPE ranged from 0.00–2.37%. Compared to three-phase scanning, dual-phase enhanced scanning without TUE resulted in a 35.70% reduction in radiation dose. Conclusion : Lung parameters calculated from VUE images using deep learning-based segmentation demonstrated strong agreement with those derived from TUE, with minimal differences, high correlation, and low bias and MAPE. dual-energy CT lung lobar segmentation artificial intelligence Deep learning virtual unenhanced images true unenhanced images Figures Figure 1 Figure 2 Figure 3 1. Introduction Unenhanced computed chest tomography (CT) is among the most frequently employed diagnostic modalities in clinical practice. The images it provides yield critical diagnostic information for a variety of pulmonary conditions and represent the first-line imaging modality for the detection of pulmonary nodules, interstitial pneumonia, and chronic obstructive pulmonary disease (COPD). Unenhanced CT images are also widely utilized in automated segmentation tasks to quantify lung volume, weight, and to evaluate pulmonary ventilation. In the study by Tan et al. ( 1 ) , segmentation of pulmonary lobes prior to nodule detection was identified as a crucial step for accurately delineating lobar anatomical structures and isolating regions associated with nodules. Furthermore, quantitative assessment of total lung volume and weight allows for visual evaluation of diseases such as COPD ( 2 ) , pulmonary fibrosis ( 3 ) , and pulmonary edema ( 4 ) , thereby providing objective support for the diagnosis and therapeutic decision-making. Because segmentation and quantification of lung tissue in various ventilation zones are CT-attenuation-dependent, utilizing unenhanced lung images for segmentation enables more accurate extraction of quantitative parameters corresponding to different ventilatory regions. However, in cases involving pulmonary vasculature or neoplastic lesions, both unenhanced and dual-phase contrast-enhanced scans are typically required, which raises concerns regarding the cumulative radiation dose received by patients. Dual-energy CT-based virtual unenhanced (VUE) imaging offers a potential solution to this issue. In pulmonary CT imaging, VUE images yield CT attenuation that are comparable to those from true unenhanced (TUE) scans. Subjective image quality assessments and tissue-specific contrast-to-noise ratio (CNR) measurements reveal no significant differences between VUE and TUE images, satisfying clinical diagnostic requirements while reducing radiation exposure by approximately one-third ( 5 , 6 ) . Most previous studies on dual-energy CT VUE imaging in the lungs have primarily focused on evaluating CT attenuations or image quality ( 7 ) . However, relatively few have addressed the accuracy or variability of artificial intelligence (AI)-based automated segmentation techniques, particularly those based on deep learning. Therefore, this study aims to apply a deep learning-based automatic lung segmentation algorithm to both VUEs (arterial-phase VUE [AP-VUE], and venous-phase VUE [VP-VUE]) and TUE images, in order to calculate lung volume, weight, and functional parameters. The study will further compare the differences, correlations, bias, and mean absolute percentage error (MAPE) among three imaging types (TUE, AP-VUE, and VP-VUE), thereby evaluating the feasibility of using dual-energy CT VUE imaging in automatic segmentation applications. 2. Materials and Methods 2.1 Participants The retrospective study was approved by the Ethics Committee of Nanjing Drum Tower Hospital (Approval No:2022-449-02), with a waiver of informed consent. A total of 245 patients who underwent multiphase dual-energy chest CT scans—including both unenhanced and contrast-enhanced phases—for clinically suspected pulmonary lesions between January 2024 and October 2024 were identified through the hospital’s Picture Archiving and Communication System. Cases were excluded based on the following criteria: 15 cases with severe respiratory motion artifacts in at least one phase, and 7 cases with insufficient scan coverage or incomplete inclusion of lung tissue in at least one phases. Figure 1 illustrates the flow of this study. 2.2 Scanning Protocol All scans were performed on a 128-row CT scanner (GE Revolution CT ES, GE Healthcare, Waukesha, USA). Each patient underwent a unenhanced scan followed by dual-phase contrast-enhanced scans during the arterial and venous phases. The scan range for all three phases extended from the thoracic inlet to the lung bases and was performed during breath-holding after inspiration. Non-contrast scan parameters included a tube voltage of 120 kVp, automatic tube current modulation with a current range of 50–350 mA, and a noise index of 10. The detector coverage was 80 mm, rotation time was 0.5 s/rot, and pitch was set at 0.992:1. Contrast-enhanced scans were acquired using Gemstone Spectral Imaging (GSI) mode, a single-source rapid switching dual-energy mode with rapid tube voltage switching between 80 and 140 kVp and a fixed tube current of 320 mA. All other scanning parameters were consistent with those used for the unenhanced scans. The contrast agent iohexol (350 mgI/mL, GE Healthcare, Shanghai, China) was administered intravenously at a rate of 2.5–3.0 mL/s, with a dose adjusted according to patient body weight (1-1.5mL/kg) ( 8 ) . Arterial phase images were performed 30 seconds after injection, followed by venous phase imaging at 65–70 seconds post-injection. Routine unenhanced lung images were reconstructed using 40% Adaptive Statistical Iterative Reconstruction-V (ASIR-V) and designated as TUE images. VUE generated from dual-phase contrast-enhanced scans using the same 40% ASIR-V reconstruction algorithm were referred to as AP-VUE and VP-VUE. All images were reconstructed with a slice thickness and interval of 1.25 mm. 2.3 Lung segmentation 2.3.1 Lung lobar segmentation Lobar segmentation was conducted using a deep learning-based medical image segmentation model (Visual Basic .NET, VB-Net) with an AI-powered lung lobe segmentation software (version 1.1, United Imaging, Shanghai, China; developed by Wu J) ( 9 ) . The three sets of DICOM images —TUE, AP-VUE, and VP-VUE—were imported into the software, and a 3D segmentation task was created to perform batch processing of the datasets. Upon completion, the software automatically output the volume and weight of the five lung lobes: left upper lobe (LUL), left lower lobe (LLL), right upper lobe (RUL), right middle lobe (RML), and right lower lobe (RLL). The sum of these lobar volume and weight represented the total lung volume and total lung weight, respectively. The volume proportion and weight proportion of each lobe were defined as the ratio of its volume/weight to the total lung volume/weight. 2.3.2 Pulmonary Ventilation Assessment Pulmonary ventilation function was assessed using a custom-developed algorithm. Initially, DICOM series data were imported, and a whole-lung segmentation mask was generated using a U-Net-based model. Separate U-Net-based models were employed to segment masks of pulmonary vessels and trachea. Subsequently, the vessel and tracheal masks were subtracted from the whole-lung mask to obtain a lung parenchyma mask excluding these structures. Within this mask, lung ventilation regions were classified based on CT attenuations as follows: hyperventilation region (CT ≤ -950 HU), normal ventilation region (-950 HU < CT ≤ -500 HU), poor ventilation region (-500 HU -100 HU). The volume and weight of each region were quantified, and their proportions relative to the total lung volume and weight were calculated. The algorithm was implemented in Python 3. 2.4 Radiation Dose Following each scan, the scanner automatically recorded the CT Dose Index Volume (CTDIvol) and Dose Length Product (DLP) for unenhanced scan as well as the arterial phase and venous phase scans. The patient’s radiation exposure was quantified using the Effective Dose (ED), calculated by the formula ED = k × DLP. where the conversion coefficient k = 0.014 mSv/(mGy·cm) ( 10 ) . The with TUE radiation dose was defined as the sum of radiation dose from the unenhanced scan and both contrast-enhanced phases. The without TUE radiation dose was calculated as the sum of radiation dose from the dual-phase contrast-enhanced scans. 2.5 Statistical Analysis Statistical analyses were conducted using Python 3 with the packages scipy, statsmodels, and pingouin. The significance level was set at P < 0.05 for all tests. The Shapiro-Wilk test was employed to assess the normality of continuous variables. Variables conforming to a normally distributed were expressed as mean ± standard deviation, while non-normally distributed variables were reported as median with interquartile range or as percentages. Differences across multiple groups for normally distributed variables were evaluated using a Linear Mixed-Effects Model (LMM), followed by pairwise comparisons with Tukey’s Honest Significant Difference (HSD) test. For non-normally distributed variables, a Generalized Linear Mixed Model (GLMM) was applied, with pairwise comparisons also performed using Tukey’s HSD test. Pearson’s correlation analysis was used to assess relationships between variables, with correlation coefficients interpreted as follows: very strong: 0.8–1.0; strong: 0.6–0.8; moderate: 0.4–0.6; weak: 0.2–0.4; very weak/no correlation: 0.0–0.2. To assess the agreement between metrics derived from AP-VUE and VP-VUE images relative to those from TUE images, average Bias and Mean Absolute Percentage Error (MAPE) were calculated: $$\:Bias=\:\frac{1}{n}\sum\:_{i=1}^{n}({VUE}_{i}-{TUE}_{i})$$ $$\:MAPE=\:\frac{1}{n}\sum\:_{i=1}^{n}\left|\frac{{TUE}_{i}-{VUE}_{i}}{{TUE}_{i}}\right|*100\%$$ where, n is the sample size, \(\:{VUE}_{i}\) represents the parameter value computed from the VUE image for the i -th sample, and \(\:{TUE}_{i}\) represents the corresponding parameter value computed from the TUE image for the same sample. 3. Results 3.1 General Characteristics Out of 245 eligible patients, 22 were excluded, resulting in a final cohort of 223 patients, including 129 males and 94 females, with a mean age of 58 ± 13 years. The clinical characteristics of the cohort were as follows: 103 cases of pulmonary nodules, 37 cases of emphysema, 21 cases of interstitial pneumonia, 3 cases of chronic obstructive pulmonary disease, 4 cases of lung squamous cell carcinoma, 5 cases of lung adenocarcinoma, 7 cases of pulmonary infections, and 43 cases classified as other conditions. The ED for scans with and without TUE were 13.67 ± 1.62 mSv and 8.79 ± 0.81 mSv, respectively, with omission of TUE scanning resulting in a 35.70% reduction in radiation dose. Table 1 summarizes the baseline characteristics of patients. Table 1 Patient Demographics, Radiation Dose, and Clinical Characteristics Items Value Gender (male / female) 129 / 94 Age (years) 58 ± 13 Height (cm) 164.29 ± 10.34 Weight (kg) 68.52 ± 9.85 DLP (mGy·cm) 976.17 ± 115.62 T+A+V , 627.54 ± 57.58 A+V ED (mSv) 13.67 ± 1.62 T+A+V , 8.79 ± 0.81 A+V Clinical (n = 223) pulmonary nodules (n) 103 emphysema (n) 37 interstitial pneumonia (n) 21 chronic obstructive pulmonary disease (n) 3 lung squamous cell carcinoma (n) 4 lung adenocarcinoma (n) 5 pulmonary infections (n) 7 other conditions (n) 43 Note: T , True unenhanced scan; A , arterial phase scan; V , venous phase scan. 3.2 Comparison of Difference between TUE and VUE The total lung volumes derived from TUE, AP-VUE, and VP-VUE images were 4429.08 ± 1296.15 mL, 4330.97 ± 1337.12 mL, and 4333.81 ± 1323.25 mL, respectively, while the total lung weights were 878.58 ± 171.22 g, 861.19 ± 161.80 g, and 868.44 ± 158.06 g, respectively. The volume and weight proportions of each lung lobe, as well as those of the four ventilation regions are detailed in Table 2 . The normal ventilation weight proportion of TUE differed significantly from that of AP-VUE ( P < 0.05). The poor ventilation weight proportion of TUE showed significant differences compared to both AP-VUE and VP-VUE (both, P 0.05). Figure 2 illustrates an example of lung segmentation. Table 2 Comparison of Quantitative CT Parameters Among TUE, AP-VUE, and VP-VUE Item TUE AP-VUE VP-VUE P T-A P T-V P A-V volume total (mL) 4429.08 ± 1296.15 4330.97 ± 1337.12 4333.81 ± 1323.25 0.71 0.73 1.00 weight total (g) 878.58 ± 171.22 861.19 ± 161.8 868.44 ± 158.06 0.50 0.79 0.89 Lobe relative volume (%) Left upper 24.76 ± 4.01 24.88 ± 4.01 24.82 ± 4.03 0.95 0.99 0.99 Left lower 20.99 ± 4.03 20.84 ± 4.12 20.84 ± 3.95 0.92 0.92 1.00 Right upper 21.07 ± 4.36 21.07 ± 4.31 21.10 ± 4.30 1.00 1.00 1.00 Right middle 9.93 ± 2.40 10.10 ± 2.47 10.11 ± 2.47 0.75 0.71 1.00 Right lower 23.26 ± 4.04 23.12 ± 3.95 23.13 ± 3.91 0.93 0.94 1.00 Lobe relative weight (%) Left upper 23.16 ± 2.88 23.20 ± 2.95 23.15 ± 2.93 0.99 1.00 0.98 Left lower 23.78 ± 3.61 23.77 ± 3.51 23.74 ± 3.47 1.00 0.99 1.00 Right upper 19.09 ± 3.27 18.95 ± 3.27 19.06 ± 3.32 0.89 0.99 0.93 Right middle 8.85 ± 2.02 8.95 ± 2.05 8.96 ± 2.05 0.86 0.85 1.00 Right lower 25.12 ± 3.33 25.13 ± 3.19 25.09 ± 3.17 1.00 0.99 0.99 Ventilation region volume proportion (%) Hyper 2.72 ± 4.12 2.83 ± 4.19 2.83 ± 4.19 0.96 0.96 1.00 Normal 93.75 ± 4.88 93.18 ± 4.89 93.15 ± 5.08 0.44 0.40 1.00 Poor 2.59 ± 2.33 2.97 ± 2.16 3.00 ± 2.42 0.19 0.15 0.99 Non 0.94 ± 0.81 1.02 ± 0.76 1.02 ± 0.82 0.55 0.55 1.00 Ventilation region weight proportion (%) Hyper 0.53 ± 1.19 0.55 ± 1.24 0.55 ± 1.18 0.98 0.99 1.00 Normal 85.52 ± 7.06 83.90 ± 6.89 84.06 ± 7.21 0.04 0.07 0.97 Poor 8.82 ± 4.43 10.06 ± 4.24 9.98 ± 4.47 0.01 0.02 0.98 Non 5.12 ± 3.05 5.48 ± 3.18 5.42 ± 3.34 0.45 0.58 0.98 3.3 Correlation Between TUE and VUE Metrics Correlation analyses among TUE, AP-VUE, and VP-VUE datasets revealed statistically significant correlations (all P < 0.05). Specifically, the comparison between TUE and AP-VUE showed correlation coefficients of 0.97 for total lung volume and 0.99 for total lung weight. The volume proportions and weight proportions of individual lung lobes exhibited correlation coefficients ranging from 0.97 to 0.99. For the four ventilation regions, the volume proportions correlated between 0.83 and 0.98, while the weight proportions ranged from 0.75 to 0.98. Similarly, comparison between AP-VUE and VP-VUE yielded correlation coefficients of 0.98 for total lung volume and 0.99 for total volume weight. The relative volume and weight proportions of lung lobes ranged from 0.98 to 0.99, and the volume and weight proportions of the four ventilation regions exhibited correlation coefficients of 0.92–0.99 and 0.90–0.99, respectively. Figure 3 illustrates the correlation comparisons of volume and weight proportions of lung lobes and ventilation regions among TUE, AP-VUE, and VP-VUE. Detailed correlation values are provided in Table 3 . Table 3 Correlation Between TUE and VUE. Items TUE vs VUEA TUE vs VUEV VUEA vs VUEV Pearson Corr P Pearson Corr P Pearson Corr P volume total (mL) 0.97 < 0.001 0.97 < 0.001 0.98 < 0.001 weight total (g) 0.99 < 0.001 0.99 < 0.001 0.99 < 0.001 Lobe relative volume (%) Left upper 0.98 < 0.001 0.98 < 0.001 0.98 < 0.001 Left lower 0.98 < 0.001 0.98 < 0.001 0.98 < 0.001 Right upper 0.99 < 0.001 0.99 < 0.001 0.99 < 0.001 Right middle 0.98 < 0.001 0.98 < 0.001 0.98 < 0.001 Right lower 0.97 < 0.001 0.97 < 0.001 0.98 < 0.001 Lobe relative weight (%) Left upper 0.97 < 0.001 0.97 < 0.001 0.98 < 0.001 Left lower 0.98 < 0.001 0.98 < 0.001 0.99 < 0.001 Right upper 0.99 < 0.001 0.99 < 0.001 0.99 < 0.001 Right middle 0.98 < 0.001 0.99 < 0.001 0.99 < 0.001 Right lower 0.98 < 0.001 0.98 < 0.001 0.99 < 0.001 Ventilation region volume proportion (%) Hyper 0.97 < 0.001 0.98 < 0.001 0.99 < 0.001 Normal 0.93 < 0.001 0.95 < 0.001 0.97 < 0.001 Poor 0.90 < 0.001 0.93 < 0.001 0.92 < 0.001 Non 0.83 < 0.001 0.84 < 0.001 0.92 < 0.001 Ventilation region weight proportion (%) Hyper 0.98 < 0.001 0.98 < 0.001 0.99 < 0.001 Normal 0.82 < 0.001 0.86 < 0.001 0.92 < 0.001 Poor 0.85 < 0.001 0.89 < 0.001 0.92 < 0.001 Non 0.75 < 0.001 0.76 < 0.001 0.90 < 0.001 3.4 Bias and MAPE Between TUE and VUE The biases of total lung volume calculated by comparing TUE with AP-VUE and VP-VUE were − 98.11 mL and − 95.27 mL, respectively, while the biases for total lung weight were − 17.39 g and − 10.14 g, respectively. The MAPEs for total lung volume were 2.37% and 2.15%, and for total lung weight were 1.80% and 0.89%, respectively. When comparing TUE with VUE, the biases of relative volume and weight proportions for each lung lobe ranged from − 0.18 to + 0.18, with corresponding MAPEs between 0.00% and 1.90%. For the ventilation regions, volume proportion biases ranged from − 0.60 to 0.41, and weight proportion biases ranged from − 1.62 to 1.23. The normal ventilation region exhibited the lowest MAPE values for volume proportion at 0.60% and 0.64%, whereas MAPE values for other ventilation regions exceeded 10%. Similarly, the weight proportion MAPE for the normal ventilation region was lowest at 1.74% and 1.63%, with other regions showing MAPE values above 11%. Detailed bias and MAPE values for the relative volume and weight proportions of lung lobes and the four ventilation regions are summarized in Table 4 . Table 4 Comparison of Bias and MAPE Across TUE, AP-VUE, and VP-VUE. Items Bias vs TUE MAPE vs TUE AP-VUE VP-VUE AP-VUE VP-VUE volume total (mL) -98.11 -95.27 2.37% 2.15% weight total (g) -17.39 -10.14 1.80% 0.89% Lobe relative volume (%) Left upper 0.12 0.06 0.54% 0.29% Left lower -0.15 -0.15 0.73% 0.48% Right upper 0.00 0.03 0.02% 0.19% Right middle 0.17 0.18 1.77% 1.90% Right lower -0.14 -0.12 0.32% 0.22% Lobe relative weight (%) Left upper 0.04 -0.01 0.21% 0.00% Left lower 0.00 -0.03 0.11% 0.01% Right upper -0.14 -0.03 0.85% 0.21% Right middle 0.10 0.11 1.28% 1.35% Right lower 0.00 -0.03 0.18% 0.04% Ventilation region volume proportion (%) Hyper 0.11 0.11 10.87% 10.46% Normal -0.57 -0.60 0.60% 0.64% Poor 0.38 0.41 24.09% 23.65% Non 0.08 0.08 21.24% 19.24% Ventilation region weight proportion (%) Hyper 0.02 0.01 12.33% 12.63% Normal -1.62 -1.47 1.74% 1.63% Poor 1.23 1.15 18.99% 17.18% Non 0.36 0.30 14.35% 11.50% 4. Discussion The results of this study demonstrated no significant differences in total lung volume/weight, volume/weight proportions of individual lobes, or volume proportions of ventilation regions ( P > 0.05). However, some significant differences were observed in the weight proportions of specific ventilation regions ( P < 0.05). The correlation coefficients between TUE and both AP-VUE and VP-VUE ranged from 0.75 to 0.99. Except for the volume and weight proportions of the hyperventilated, normal, and non-ventilation regions, the maximum MAPE between parameters calculated from TUE and those from VUE images was 2.15%. The virtual unenhanced imaging technology based on dual-energy CT utilizes a material decomposition algorithm to eliminate the influence of iodinated contrast from enhanced images, thereby generating unenhanced, iodine-free images that resemble conventional unenhanced CT scans. These VUE images have demonstrated potential as a feasible alternative to traditional TUE ( 11 , 12 ) . Concurrently, the advancement of artificial intelligence has ushered lung CT segmentation into an era of precision quantification analysis. Prominent deep learning architectures, such as U-Net ( 13 ) and LDD-Net ( 14 ) , have markedly improved segmentation accuracy, providing a technical foundations for multiparametric quantitative analysis of pulmonary tissues. In this study, an enhanced VB-Net model was implemented via the uRP medical image analysis platform. This model incorporates a bottleneck architecture and multi-resolution optimization strategies to achieve automated segmentation of pulmonary lobes (right upper, middle, lower; left upper, lower) across three types of images: TUE, AP-VUE, and VP-VUE. A systematic quantitative analysis was subsequently performed on lobar volume and weight proportions, as well as ventilation function parameters (normalized to total lung volume and expressed as percentages). Quantitative CT analysis revealed statistically significant differences in lobar weight proportions between TUE and AP-VUE scans within both normal ventilation regions (85.52%±7.06% vs 83.90%±6.89%) and low-ventilation regions (8.82%±4.43% vs 10.06%±4.24%) (all P < 0.05), with AP-VUE collectively accounting for approximately 93% of total pulmonary weight. Notably, the low-ventilation weight proportions in TUE scans (8.82%±4.43%) was significantly lower than that observed in VP-VUE (9.98%±4.47%, P < 0.05). This discrepancy may be attributed to residual iodine interference during AP-VUE reconstruction, caused by elevated contrast concentration in the arterial phase, potentially leading to distorted functional assessments in the − 950~-100 HU range. Conversely, the reduced iodine concentration in VP-VUE enabled effective artifact suppression within a narrower − 500~-100 HU window (10.2% of total lung volume), in line with quantitative artifact analyses by Okada et al. ( 15 ) . In a methodological innovation, this study employed deep learning-based lobar segmentation to generate difference maps of CT attenuations (-950~-500 HU) between VUE and TUE scans, providing critical anatomical insights for optimizing multiphase pulmonary CT protocols. Intriguingly. Interestingly, VP-VUE showed discrepancies from TUE only in minimal proportion of non-ventilated regions (accounting for 4.8% of total volume), further supporting its superior approximation of TUE relative to AP-VUE from a segmentation-based perspective. This finding aligns with the CT attenuation-based validation of virtual non-contrast techniques by Guo et al. ( 16 ) , confirming the higher fidelity of venous-phase over arterial-phase VUE reconstructions. TUE exhibited high correlations coefficients with both AP/VP-VUE in terms of lobar volume and weight proportions as well as volumetric proportions across different ventilation regions (r = 0.83–0.99, P < 0.001). However, slightly lower correlations were observed for non-ventilated weight proportions (r = 0.75–0.76), which may be attributed to the limited representation of non-ventilated regions—comprising only approximately 5% of total lung—thereby increasing statistical variability. Bias analysis revealed narrow ranges (-0.60 to 0.41, all < 1) across lobar volume/weight proportions and ventilation region volumetric proportions. Notably, MAPE for normal ventilation regions were exceptionally low, measuring 0.60–0.64% for volume (93% of total) and 1.63–1.74% for weight (84% of total), indicating superior error control. The integration of TUE-based lobar segmentation techniques provides high-precision imaging data for pulmonary disease research, particularly in evaluating dominant regions (93% volume and 84% weight of normal ventilation regions). Accurate lobar segmentation facilitates anatomically guided registration of individual pulmonary lobes by leveraging their functional independence, spatial isolation, and distinct respiratory kinematics. This methodological advancement substantially improves the precision of lesion localization, enhances the estimation of respiratory motion, and serves as a critical preprocessing step for advanced automated pulmonary image analysis. Conventional segmentation datasets primarily rely on unenhanced CT scans to avoid CT attenuation distortion caused by iodinated contrast agent. In this study, we integrated multiphase VUE imaging—specifically AP- and VP-VUE—with deep learning-based segmentation to assess the consistency of quantitative parameters across modalities. Using the uRP platform's fully automated multiparametric analysis—including volume, density, CT attenuation distribution—we demonstrated VUE provides quantitatively comparable results to TUE in dual-energy contrast-enhanced CT examinations. Clinically, the combination of dual-phase enhancement with VUE reconstruction resulted in a 35.70% reduction in radiation dose reduction compared to conventional triphasic imaging protocols (mean ED: 2.85 vs 4.43 mSv), aligning with radiation optimization benchmarks proposed by Strotzer et al. ( 17 ) . These findings offer strong support for the adoption of radiation-efficient enhanced-only imaging protocols without compromising the quantitative diagnostic capacity. Conventional spirometry suffers from several inherent limitations in pulmonary function assessment, including a high dependency on patient cooperation, considerable measurement variability, and an inability to evaluate function at the lobar or segmental level, thereby restricting its application to whole-lung assessments ( 18 ) .Prior studies ( 19 , 20 ) have demonstrated that quantitative analysis of unenhanced CT data enables accurate measurement of emphysematous volume and weight changes in COPD, facilitating the differentiation of emphysematous, functional, and interstitial lung tissues through visualized regional assessment. CT attenuation-based tissue segmentation provides enhanced accuracy in quantifying quantitative parameters across heterogeneous ventilation regions, thereby enhancing the comprehensive and precise evaluation of pulmonary pathologies ( 21 ) . Building on this foundations, our study integrates multiphase VUE imaging with deep learning segmentation to reveal that virtual enhanced images derived from different enhancement phases exert phase-dependent influences on weight proportions distribution across ventilation regions. This phase-related variation underscores the need for careful consideration in clinical settings, particularly when selecting optimized imaging protocols tailored to specific pulmonary disease assessment. This study acknowledges three primary technical limitations within its validation framework: (1) The absence of a systematic comparison between enhanced CT-based segmentation algorithms and gold-standard unenhanced imaging, particularly in assessing the generalizability of deep learning models across different CT scanner vendors; (2) The current analysis of spatial heterogeneity using VUE technology is limited to the lobar level and lacks evaluation at the subsegmental anatomical scale, which may provide additional insights related to bronchial anatomical variations and regional hemodynamic characteristics; (3) The functional validation framework does not incorporate multimodal correlation analysis between dynamic pulmonary function parameters (e.g., DLCO, FEV1) and CT-derived quantitative indices (e.g., low-ventilation volume proportion), and is further constrained by the absence of longitudinal validation data under exercise-induced stress conditions. In conclusion, within a deep learning-based automated lobar segmentation framework, VP-VUE and conventional TUE imaging demonstrated high concordance in key anatomical and functional evaluation metrics. However, the observed differences in low-ventilation distribution characteristics highlight the need for clinical attention when selecting imaging modalities for functional pulmonary assessment. Declarations Acknowledgements All authors have reviewed the manuscript and approve to submit to your journal. (Chao Zou, Jun Hu, An Yan, Aiyun Sun, Wen Yang, Xin Peng, Xu Yang , Shangwen Yang, and Xiaoyan Xin). Author contributions Writing – Original Draft Preparation: Chao Zou, Jun Hu, An Yan. Data Curation & Formal Analysis: Aiyun Sun, Wen Yang, Xin Peng, Xu Yang. Writing – Review & Editing: Shangwen Yang, Xiaoyan Xin. All authors reviewed and approved the final manuscript. FUNDING This study was supported in part by fundings for Clinical Trials from the Affiliated Drum Tower Hospital, Medical School of Nanjing University (2023-LCYJ-PY-26) ，Nanjing health science and technology development special fund major project (ZKX22015)，and Key Projects for the Development of New Medical Technologies from the Affiliated Drum Tower Hospital, Medical School of Nanjing University (XJSFZLX202313). Data availability The data that support the findings of this study are available from the corresponding author upon reasonable request. Ethical approval The study was approved by the Medical Ethics Committee of the Nanjing Drum Tower Hospital (Approval No:2022-449-02). Ethics declaration The study was conducted in accordance with the “Declaration of Helsinki”. Consent to participate The need for informed consent was waived due to the retrospective nature of the study. Consent to publish All authors have agreed to the submission of this manuscript for publication. Furthermore, the authors declare that there are no conflicts of interest related to the publication of this manuscript. Competing interests The authors declare no competing interests. References de Margerie-Mellon C, Chassagnon G. Artificial intelligence: A critical review of applications for lung nodule and lung cancer. Diagn Interv Imaging. 2023;104(1):11–7. Steinhardt M, Marka AW, Ziegelmayer S, Makowski M, Braren R, Graf M et al. Comparison of Virtual Non-Contrast and True Non-Contrast CT Images Obtained by Dual-Layer Spectral CT in COPD Patients. Bioengineering. 2024;11(4). Meyer KC. Pulmonary fibrosis, part I: epidemiology, pathogenesis, and diagnosis. Expert Rev Respir Med. 2017:1–17. Coppadoro A, Leiser P, Kirschning T, Weiß C, Hagmann M, Schoettler J et al. A quantitative CT parameter for the assessment of pulmonary oedema in patients with acute respiratory distress syndrome. PLoS ONE. 2020;15(11). Bernsen MLE, Veendrick PB, Martens JM, Pijl MEJ, Hofmeijer J, van Gorp MJ. Initial experience with dual-layer detector spectral CT for diagnosis of blood or contrast after endovascular treatment for ischemic stroke. Neuroradiology. 2021;64(1):69–76. Park A, Lee YH, Seo HS. Could both intrinsic and extrinsic iodine be successfully suppressed on virtual non-contrast CT images for detecting thyroid calcification? Japanese J Radiol. 2021;39(6):580–8. Rajiah P, Parakh A, Kay F, Baruah D, Kambadakone AR, Leng S. Update on Multienergy CT: Physics, Principles, and Applications. Radiographics. 2020;40(5):1284–308. Zeng W, Tang J, Xu X, Zhang Y, Zeng L, Zhang Y, et al. Safety of non-ionic contrast media in CT examinations for out-patients: retrospective multicenter analysis of 473,482 patients. Eur Radiol. 2024;34(9):5570–7. Wu J, Xia Y, Wang X, Wei Y, Liu A, Innanje A et al. uRP: An integrated research platform for one-stop analysis of medical images. Front Radiol. 2023;3. Dixon AK. Benefits and costs, an eternal balance. Ann ICRP. 2007;37(1):1–3. Jungblut L, Sartoretti T, Kronenberg D, Mergen V, Euler A, Schmidt B et al. Performance of virtual non-contrast images generated on clinical photon-counting detector CT for emphysema quantification: proof of concept. Br J Radiol. 2022;95(1135). Wong WD, Mohammed MF, Nicolaou S, Schmiedeskamp H, Khosa F, Murray N, et al. Impact of Dual-Energy CT in the Emergency Department: Increased Radiologist Confidence, Reduced Need for Follow-Up Imaging, and Projected Cost Benefit. Am J Roentgenol. 2020;215(6):1528–38. Kumari KS, Samal S, Mishra R, Madiraju G, Mahabob MN, Shivappa AB. Diagnosing COVID-19 from CT Image of Lung Segmentation & Classification with Deep Learning Based on Convolutional Neural Networks. Wireless Pers Commun. 2021;127(3):2483–99. El-Bana S, Al-Kabbany A, Sharkas M. A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans. Diagnostics. 2020;10(3). Okada K, Matsuda M, Tsuda T, Kido T, Murata A, Nishiyama H, et al. Dual-energy computed tomography for evaluation of breast cancer: value of virtual monoenergetic images reconstructed with a noise-reduced monoenergetic reconstruction algorithm. Japanese J Radiol. 2019;38(2):154–64. Guo Y, Fan Q, Ren Z, Yu N, Tan H, Ma G. Feasibility of replacing true non-contrast images with virtual non-contrast images in quantitative analysis of emphysema. Die Radiol. 2025. Strotzer QD, Schachner C, Scheuermeyer L, Raab F, Meiler S, Malfertheiner MV et al. Quantitative chest computed tomography: regional differences in dual-energy-derived virtual vs. true non-contrast scans. Clin Radiol. 2025;85. Cornelius T. Clinical guideline highlights for the hospitalist: GOLD COPD update 2024. J Hosp Med. 2024;19(9):818–20. den Harder AM, Bangert F, van Hamersvelt RW, Leiner T, Milles J, Schilham AMR, et al. The Effects of Iodine Attenuation on Pulmonary Nodule Volumetry using Novel Dual-Layer Computed Tomography Reconstructions. Eur Radiol. 2017;27(12):5244–51. Ufuk F, Demirci M, Altinisik G, Karasu U. Quantitative analysis of Sjogren's syndrome related interstitial lung disease with different methods. Eur J Radiol. 2020;128. Zhang G, Jiang S, Yang Z, Gong L, Ma X, Zhou Z, et al. Automatic nodule detection for lung cancer in CT images: A review. Comput Biol Med. 2018;103:287–300. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 29 Oct, 2025 Reviewers agreed at journal 27 Oct, 2025 Reviewers agreed at journal 18 Sep, 2025 Reviewers invited by journal 18 Sep, 2025 Editor invited by journal 02 Sep, 2025 Editor assigned by journal 08 Aug, 2025 Submission checks completed at journal 08 Aug, 2025 First submitted to journal 05 Aug, 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-7300980","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":521760215,"identity":"0a211b44-ce42-46f3-ac63-ec1dacd78a98","order_by":0,"name":"Chao Zou","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Chao","middleName":"","lastName":"Zou","suffix":""},{"id":521760216,"identity":"0080f7aa-22cf-4207-bab8-f935c7ecdb67","order_by":1,"name":"Jun Hu","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Hu","suffix":""},{"id":521760217,"identity":"03c88b4c-c355-4ded-805e-4791ba816498","order_by":2,"name":"An Yan","email":"","orcid":"","institution":"Nanjing Gaochun people's Hospital","correspondingAuthor":false,"prefix":"","firstName":"An","middleName":"","lastName":"Yan","suffix":""},{"id":521760218,"identity":"f986f345-dc99-4801-a4c9-5ffe7245c721","order_by":3,"name":"Aiyun Sun","email":"","orcid":"","institution":"GE HealthCare China","correspondingAuthor":false,"prefix":"","firstName":"Aiyun","middleName":"","lastName":"Sun","suffix":""},{"id":521760219,"identity":"673ca2ad-6db3-41cd-b947-6ab244912630","order_by":4,"name":"Wen Yang","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Yang","suffix":""},{"id":521760220,"identity":"aa124efa-7e88-43c7-b1a2-519fed146ff5","order_by":5,"name":"Xin Peng","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Peng","suffix":""},{"id":521760221,"identity":"78f8e7cf-196b-44c4-837b-908e154b2055","order_by":6,"name":"Xu Yang","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital Clinical College of Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Yang","suffix":""},{"id":521760222,"identity":"229ae2fd-9f30-459e-a5fb-cd31bdf6ae07","order_by":7,"name":"Shangwen Yang","email":"","orcid":"","institution":"Nanjing Drum Tower Hospital, Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Shangwen","middleName":"","lastName":"Yang","suffix":""},{"id":521760223,"identity":"18d29a24-ba77-4314-a39e-d5d33a2b34b3","order_by":8,"name":"Xiaoyan Xin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYDACZhBRYSPHxt5+gBQtZ9KM+XjOJJBgE2Pb4cR5Eg4GxKk2OM57TJq3LS29TYIhgeFHxTbCWiSb+ZKNec7Z5LZJNx5g7Dlzm7AWfmYew8c8ZWm5bTIHEpgZ24jQwsbMY3CYh+1wOptEggFxWiC2tB1OIF6LZDOPseGcM2mGbcBAPkiUXwzOnzGTeFNhIy/f3n7wwY8KIrSAABMPlHGAOPVAwPiDaKWjYBSMglEwIgEAp6c2X6EiiIYAAAAASUVORK5CYII=","orcid":"","institution":"Nanjing Drum Tower Hospital, Nanjing University","correspondingAuthor":true,"prefix":"","firstName":"Xiaoyan","middleName":"","lastName":"Xin","suffix":""}],"badges":[],"createdAt":"2025-08-05 13:08:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7300980/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7300980/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92477863,"identity":"d9991944-edd1-4bd1-ab54-f8d191db7790","added_by":"auto","created_at":"2025-09-30 07:25:26","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":724925,"visible":true,"origin":"","legend":"","description":"","filename":"FeasibilityofAutomatedAccurateLungSegmentationUsingDeepLearningonVirtualUnenhancedImagesfromGemstoneSpectralCTImagingForPulmonaryVentilationAssessment.docx","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/d03055b0ab2ca4a5e4e85a04.docx"},{"id":92477861,"identity":"b4dfdb6f-9ac3-47e1-9658-3cdc2e13daeb","added_by":"auto","created_at":"2025-09-30 07:25:26","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9763,"visible":true,"origin":"","legend":"","description":"","filename":"c318c7cdba1349d6863160cf147e8689.json","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/19ec9901452682db4e47aa02.json"},{"id":92477866,"identity":"eea9844c-b9c7-4da4-8015-a76e85e11073","added_by":"auto","created_at":"2025-09-30 07:25:27","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":116294,"visible":true,"origin":"","legend":"","description":"","filename":"c318c7cdba1349d6863160cf147e86891enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/85a29f701ebc0d478371fc9b.xml"},{"id":92478558,"identity":"e441f710-d33f-43b3-8549-ecd371bc2458","added_by":"auto","created_at":"2025-09-30 07:33:26","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29138,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/dbfbd323f1435ca067a45f0c.png"},{"id":92478559,"identity":"21ec40a7-3ae2-471a-a9bb-053211b216d5","added_by":"auto","created_at":"2025-09-30 07:33:26","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":85274,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/0e3183ae3fe18c880aedac06.png"},{"id":92478561,"identity":"6d506195-84d2-4746-aed6-a0f20e34de48","added_by":"auto","created_at":"2025-09-30 07:33:27","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32108,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/fa14edb653ea50844094ac83.png"},{"id":92477871,"identity":"8070313d-6836-48a5-be26-50d984f11fed","added_by":"auto","created_at":"2025-09-30 07:25:27","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112182,"visible":true,"origin":"","legend":"","description":"","filename":"c318c7cdba1349d6863160cf147e86891structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/fe46658d8f440a58c94f4a68.xml"},{"id":92477870,"identity":"a95c663a-a9ea-4b4b-adff-9fa88b5c5059","added_by":"auto","created_at":"2025-09-30 07:25:27","extension":"html","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120458,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/a362dbcdf57e1e124804b073.html"},{"id":92480484,"identity":"dcd36bd9-8d58-4a26-9dbc-0e812ae82a05","added_by":"auto","created_at":"2025-09-30 07:41:26","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":164418,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of the study design. GSI, gemstone spectral imaging.\u003c/p\u003e","description":"","filename":"floatimage113.png","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/4e3a19121034c278c0edf078.png"},{"id":92477869,"identity":"2c80eb63-fb75-4d88-806c-baf243c18017","added_by":"auto","created_at":"2025-09-30 07:25:27","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":332930,"visible":true,"origin":"","legend":"\u003cp\u003eDeep learning-based segmentation performance in pulmonary imaging. (A) Segmentation of pulmonary lobes. A 54-year-old male patient with a clinical history of emphysema. (B) Segmentation of hyper ventilation regions. A 67-year-old male patient with a clinical history of Chronic Obstructive Pulmonary Disease. (C) Segmentation of normal ventilation regions. A 74-year-old male patient with a clinical history of lung squamous cell carcinoma. (D) Segmentation of poor ventilation regions. A 48-year-old male patient with a clinical history of pneumoconiosis. (E) Segmentation of non ventilation regions. A 50-year-old male patient with a clinical history of interstitial pneumonia.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/f28a7f0b7e2c9a20fc8c75e4.png"},{"id":92477867,"identity":"88c9e676-3dd4-4575-a1cd-8c74895e9023","added_by":"auto","created_at":"2025-09-30 07:25:27","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":180037,"visible":true,"origin":"","legend":"\u003cp\u003ePearson’s correlation coefficients among TUE, AP-VUE, and VP-VUE.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/f99b4905f3fdac3cbd2d27c2.png"},{"id":92481276,"identity":"156ae585-adf8-42bb-9a54-a4ee24891294","added_by":"auto","created_at":"2025-09-30 07:49:28","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1696998,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7300980/v1/0fab2ca7-ab54-442d-a077-ddcb3730f977.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Feasibility of Automated Accurate Lung Segmentation Using Deep Learning on Virtual Unenhanced Images from Gemstone Spectral CT Imaging For Pulmonary Ventilation Assessment","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eUnenhanced computed chest tomography (CT) is among the most frequently employed diagnostic modalities in clinical practice. The images it provides yield critical diagnostic information for a variety of pulmonary conditions and represent the first-line imaging modality for the detection of pulmonary nodules, interstitial pneumonia, and chronic obstructive pulmonary disease (COPD). Unenhanced CT images are also widely utilized in automated segmentation tasks to quantify lung volume, weight, and to evaluate pulmonary ventilation. In the study by Tan et al. \u003csup\u003e(\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e)\u003c/sup\u003e, segmentation of pulmonary lobes prior to nodule detection was identified as a crucial step for accurately delineating lobar anatomical structures and isolating regions associated with nodules. Furthermore, quantitative assessment of total lung volume and weight allows for visual evaluation of diseases such as COPD \u003csup\u003e(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e)\u003c/sup\u003e, pulmonary fibrosis \u003csup\u003e(\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e)\u003c/sup\u003e, and pulmonary edema \u003csup\u003e(\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e)\u003c/sup\u003e, thereby providing objective support for the diagnosis and therapeutic decision-making. Because segmentation and quantification of lung tissue in various ventilation zones are CT-attenuation-dependent, utilizing unenhanced lung images for segmentation enables more accurate extraction of quantitative parameters corresponding to different ventilatory regions. However, in cases involving pulmonary vasculature or neoplastic lesions, both unenhanced and dual-phase contrast-enhanced scans are typically required, which raises concerns regarding the cumulative radiation dose received by patients.\u003c/p\u003e\u003cp\u003eDual-energy CT-based virtual unenhanced (VUE) imaging offers a potential solution to this issue. In pulmonary CT imaging, VUE images yield CT attenuation that are comparable to those from true unenhanced (TUE) scans. Subjective image quality assessments and tissue-specific contrast-to-noise ratio (CNR) measurements reveal no significant differences between VUE and TUE images, satisfying clinical diagnostic requirements while reducing radiation exposure by approximately one-third \u003csup\u003e(\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e)\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eMost previous studies on dual-energy CT VUE imaging in the lungs have primarily focused on evaluating CT attenuations or image quality\u003csup\u003e(\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e)\u003c/sup\u003e. However, relatively few have addressed the accuracy or variability of artificial intelligence (AI)-based automated segmentation techniques, particularly those based on deep learning. Therefore, this study aims to apply a deep learning-based automatic lung segmentation algorithm to both VUEs (arterial-phase VUE [AP-VUE], and venous-phase VUE [VP-VUE]) and TUE images, in order to calculate lung volume, weight, and functional parameters. The study will further compare the differences, correlations, bias, and mean absolute percentage error (MAPE) among three imaging types (TUE, AP-VUE, and VP-VUE), thereby evaluating the feasibility of using dual-energy CT VUE imaging in automatic segmentation applications.\u003c/p\u003e"},{"header":"2. Materials and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1 Participants\u003c/h2\u003e\u003cp\u003e The retrospective study was approved by the Ethics Committee of Nanjing Drum Tower Hospital (Approval No:2022-449-02), with a waiver of informed consent. A total of 245 patients who underwent multiphase dual-energy chest CT scans\u0026mdash;including both unenhanced and contrast-enhanced phases\u0026mdash;for clinically suspected pulmonary lesions between January 2024 and October 2024 were identified through the hospital\u0026rsquo;s Picture Archiving and Communication System. Cases were excluded based on the following criteria: 15 cases with severe respiratory motion artifacts in at least one phase, and 7 cases with insufficient scan coverage or incomplete inclusion of lung tissue in at least one phases. Figure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e illustrates the flow of this study.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2 Scanning Protocol\u003c/h2\u003e\u003cp\u003eAll scans were performed on a 128-row CT scanner (GE Revolution CT ES, GE Healthcare, Waukesha, USA). Each patient underwent a unenhanced scan followed by dual-phase contrast-enhanced scans during the arterial and venous phases. The scan range for all three phases extended from the thoracic inlet to the lung bases and was performed during breath-holding after inspiration. Non-contrast scan parameters included a tube voltage of 120 kVp, automatic tube current modulation with a current range of 50\u0026ndash;350 mA, and a noise index of 10. The detector coverage was 80 mm, rotation time was 0.5 s/rot, and pitch was set at 0.992:1. Contrast-enhanced scans were acquired using Gemstone Spectral Imaging (GSI) mode, a single-source rapid switching dual-energy mode with rapid tube voltage switching between 80 and 140 kVp and a fixed tube current of 320 mA. All other scanning parameters were consistent with those used for the unenhanced scans. The contrast agent iohexol (350 mgI/mL, GE Healthcare, Shanghai, China) was administered intravenously at a rate of 2.5\u0026ndash;3.0 mL/s, with a dose adjusted according to patient body weight (1-1.5mL/kg) \u003csup\u003e(\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e)\u003c/sup\u003e. Arterial phase images were performed 30 seconds after injection, followed by venous phase imaging at 65\u0026ndash;70 seconds post-injection.\u003c/p\u003e\u003cp\u003eRoutine unenhanced lung images were reconstructed using 40% Adaptive Statistical Iterative Reconstruction-V (ASIR-V) and designated as TUE images. VUE generated from dual-phase contrast-enhanced scans using the same 40% ASIR-V reconstruction algorithm were referred to as AP-VUE and VP-VUE. All images were reconstructed with a slice thickness and interval of 1.25 mm.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e2.3 Lung segmentation\u003c/h2\u003e\u003cdiv id=\"Sec6\" class=\"Section3\"\u003e\u003ch2\u003e2.3.1 Lung lobar segmentation\u003c/h2\u003e\u003cp\u003eLobar segmentation was conducted using a deep learning-based medical image segmentation model (Visual Basic .NET, VB-Net) with an AI-powered lung lobe segmentation software (version 1.1, United Imaging, Shanghai, China; developed by Wu J) \u003csup\u003e(\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e)\u003c/sup\u003e. The three sets of DICOM images \u0026mdash;TUE, AP-VUE, and VP-VUE\u0026mdash;were imported into the software, and a 3D segmentation task was created to perform batch processing of the datasets. Upon completion, the software automatically output the volume and weight of the five lung lobes: left upper lobe (LUL), left lower lobe (LLL), right upper lobe (RUL), right middle lobe (RML), and right lower lobe (RLL). The sum of these lobar volume and weight represented the total lung volume and total lung weight, respectively. The volume proportion and weight proportion of each lobe were defined as the ratio of its volume/weight to the total lung volume/weight.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec7\" class=\"Section3\"\u003e\u003ch2\u003e2.3.2 Pulmonary Ventilation Assessment\u003c/h2\u003e\u003cp\u003ePulmonary ventilation function was assessed using a custom-developed algorithm. Initially, DICOM series data were imported, and a whole-lung segmentation mask was generated using a U-Net-based model. Separate U-Net-based models were employed to segment masks of pulmonary vessels and trachea. Subsequently, the vessel and tracheal masks were subtracted from the whole-lung mask to obtain a lung parenchyma mask excluding these structures. Within this mask, lung ventilation regions were classified based on CT attenuations as follows: hyperventilation region (CT \u0026le; -950 HU), normal ventilation region (-950 HU\u0026thinsp;\u0026lt;\u0026thinsp;CT \u0026le; -500 HU), poor ventilation region (-500 HU\u0026thinsp;\u0026lt;\u0026thinsp;CT \u0026le; -100 HU), and non-ventilation region (CT \u0026gt;-100 HU). The volume and weight of each region were quantified, and their proportions relative to the total lung volume and weight were calculated. The algorithm was implemented in Python 3.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e2.4 Radiation Dose\u003c/h2\u003e\u003cp\u003eFollowing each scan, the scanner automatically recorded the CT Dose Index Volume (CTDIvol) and Dose Length Product (DLP) for unenhanced scan as well as the arterial phase and venous phase scans. The patient\u0026rsquo;s radiation exposure was quantified using the Effective Dose (ED), calculated by the formula ED\u0026thinsp;=\u0026thinsp;k \u0026times; DLP. where the conversion coefficient k\u0026thinsp;=\u0026thinsp;0.014 mSv/(mGy\u0026middot;cm) \u003csup\u003e(\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e)\u003c/sup\u003e. The with TUE radiation dose was defined as the sum of radiation dose from the unenhanced scan and both contrast-enhanced phases. The without TUE radiation dose was calculated as the sum of radiation dose from the dual-phase contrast-enhanced scans.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e2.5 Statistical Analysis\u003c/h2\u003e\u003cp\u003eStatistical analyses were conducted using Python 3 with the packages scipy, statsmodels, and pingouin. The significance level was set at \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05 for all tests. The Shapiro-Wilk test was employed to assess the normality of continuous variables. Variables conforming to a normally distributed were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation, while non-normally distributed variables were reported as median with interquartile range or as percentages. Differences across multiple groups for normally distributed variables were evaluated using a Linear Mixed-Effects Model (LMM), followed by pairwise comparisons with Tukey\u0026rsquo;s Honest Significant Difference (HSD) test. For non-normally distributed variables, a Generalized Linear Mixed Model (GLMM) was applied, with pairwise comparisons also performed using Tukey\u0026rsquo;s HSD test. Pearson\u0026rsquo;s correlation analysis was used to assess relationships between variables, with correlation coefficients interpreted as follows: very strong: 0.8\u0026ndash;1.0; strong: 0.6\u0026ndash;0.8; moderate: 0.4\u0026ndash;0.6; weak: 0.2\u0026ndash;0.4; very weak/no correlation: 0.0\u0026ndash;0.2. To assess the agreement between metrics derived from AP-VUE and VP-VUE images relative to those from TUE images, average Bias and Mean Absolute Percentage Error (MAPE) were calculated:\u003cdiv id=\"Equa\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equa\" name=\"EquationSource\"\u003e\n$$\\:Bias=\\:\\frac{1}{n}\\sum\\:_{i=1}^{n}({VUE}_{i}-{TUE}_{i})$$\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Equb\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equb\" name=\"EquationSource\"\u003e\n$$\\:MAPE=\\:\\frac{1}{n}\\sum\\:_{i=1}^{n}\\left|\\frac{{TUE}_{i}-{VUE}_{i}}{{TUE}_{i}}\\right|*100\\%$$\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003ewhere, \u003cem\u003en\u003c/em\u003e is the sample size, \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{VUE}_{i}\\)\u003c/span\u003e\u003c/span\u003e represents the parameter value computed from the VUE image for the \u003cem\u003ei\u003c/em\u003e-th sample, and \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{TUE}_{i}\\)\u003c/span\u003e\u003c/span\u003e represents the corresponding parameter value computed from the TUE image for the same sample.\u003c/p\u003e\u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003e3.1 General Characteristics\u003c/h2\u003e\u003cp\u003eOut of 245 eligible patients, 22 were excluded, resulting in a final cohort of 223 patients, including 129 males and 94 females, with a mean age of 58\u0026thinsp;\u0026plusmn;\u0026thinsp;13 years. The clinical characteristics of the cohort were as follows: 103 cases of pulmonary nodules, 37 cases of emphysema, 21 cases of interstitial pneumonia, 3 cases of chronic obstructive pulmonary disease, 4 cases of lung squamous cell carcinoma, 5 cases of lung adenocarcinoma, 7 cases of pulmonary infections, and 43 cases classified as other conditions. The ED for scans with and without TUE were 13.67\u0026thinsp;\u0026plusmn;\u0026thinsp;1.62 mSv and 8.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.81 mSv, respectively, with omission of TUE scanning resulting in a 35.70% reduction in radiation dose. Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e summarizes the baseline characteristics of patients.\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\u003ePatient Demographics, Radiation Dose, and Clinical Characteristics\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"2\"\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eItems\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eValue\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGender (male / female)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e129 / 94\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge (years)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e58\u0026thinsp;\u0026plusmn;\u0026thinsp;13\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHeight (cm)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e164.29\u0026thinsp;\u0026plusmn;\u0026thinsp;10.34\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWeight (kg)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e68.52\u0026thinsp;\u0026plusmn;\u0026thinsp;9.85\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDLP (mGy\u0026middot;cm)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e976.17\u0026thinsp;\u0026plusmn;\u0026thinsp;115.62 \u003csup\u003eT+A+V\u003c/sup\u003e, 627.54\u0026thinsp;\u0026plusmn;\u0026thinsp;57.58 \u003csup\u003eA+V\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eED (mSv)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e13.67\u0026thinsp;\u0026plusmn;\u0026thinsp;1.62 \u003csup\u003eT+A+V\u003c/sup\u003e, 8.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.81 \u003csup\u003eA+V\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClinical (n\u0026thinsp;=\u0026thinsp;223)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003epulmonary nodules (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e103\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eemphysema (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e37\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003einterstitial pneumonia (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e21\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003echronic obstructive pulmonary disease (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003elung squamous cell carcinoma (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003elung adenocarcinoma (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003epulmonary infections (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eother conditions (n)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e43\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"2\"\u003eNote: \u003csup\u003eT\u003c/sup\u003e, True unenhanced scan; \u003csup\u003eA\u003c/sup\u003e, arterial phase scan; \u003csup\u003eV\u003c/sup\u003e, venous phase scan.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003e3.2 Comparison of Difference between TUE and VUE\u003c/h2\u003e\u003cp\u003eThe total lung volumes derived from TUE, AP-VUE, and VP-VUE images were 4429.08\u0026thinsp;\u0026plusmn;\u0026thinsp;1296.15 mL, 4330.97\u0026thinsp;\u0026plusmn;\u0026thinsp;1337.12 mL, and 4333.81\u0026thinsp;\u0026plusmn;\u0026thinsp;1323.25 mL, respectively, while the total lung weights were 878.58\u0026thinsp;\u0026plusmn;\u0026thinsp;171.22 g, 861.19\u0026thinsp;\u0026plusmn;\u0026thinsp;161.80 g, and 868.44\u0026thinsp;\u0026plusmn;\u0026thinsp;158.06 g, respectively. The volume and weight proportions of each lung lobe, as well as those of the four ventilation regions are detailed in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The normal ventilation weight proportion of TUE differed significantly from that of AP-VUE (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). The poor ventilation weight proportion of TUE showed significant differences compared to both AP-VUE and VP-VUE (both, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). For all other parameters, no significant differences were observed between TUE and either AP-VUE or VP-VUE, nor between AP-VUE and VP-VUE (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). Figure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e illustrates an example of lung segmentation.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eComparison of Quantitative CT Parameters Among TUE, AP-VUE, and VP-VUE\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=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eItem\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTUE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAP-VUE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eVP-VUE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP T-A\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP T-V\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eP A-V\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003evolume total (mL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4429.08\u0026thinsp;\u0026plusmn;\u0026thinsp;1296.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4330.97\u0026thinsp;\u0026plusmn;\u0026thinsp;1337.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4333.81\u0026thinsp;\u0026plusmn;\u0026thinsp;1323.25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.71\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.73\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eweight total (g)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e878.58\u0026thinsp;\u0026plusmn;\u0026thinsp;171.22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e861.19\u0026thinsp;\u0026plusmn;\u0026thinsp;161.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e868.44\u0026thinsp;\u0026plusmn;\u0026thinsp;158.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.79\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.89\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLobe relative volume (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e24.76\u0026thinsp;\u0026plusmn;\u0026thinsp;4.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e24.88\u0026thinsp;\u0026plusmn;\u0026thinsp;4.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e24.82\u0026thinsp;\u0026plusmn;\u0026thinsp;4.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e20.99\u0026thinsp;\u0026plusmn;\u0026thinsp;4.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e20.84\u0026thinsp;\u0026plusmn;\u0026thinsp;4.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e20.84\u0026thinsp;\u0026plusmn;\u0026thinsp;3.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e21.07\u0026thinsp;\u0026plusmn;\u0026thinsp;4.36\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e21.07\u0026thinsp;\u0026plusmn;\u0026thinsp;4.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e21.10\u0026thinsp;\u0026plusmn;\u0026thinsp;4.30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight middle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e9.93\u0026thinsp;\u0026plusmn;\u0026thinsp;2.40\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e10.10\u0026thinsp;\u0026plusmn;\u0026thinsp;2.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e10.11\u0026thinsp;\u0026plusmn;\u0026thinsp;2.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.71\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23.26\u0026thinsp;\u0026plusmn;\u0026thinsp;4.04\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e23.12\u0026thinsp;\u0026plusmn;\u0026thinsp;3.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e23.13\u0026thinsp;\u0026plusmn;\u0026thinsp;3.91\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.94\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLobe relative weight (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23.16\u0026thinsp;\u0026plusmn;\u0026thinsp;2.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e23.20\u0026thinsp;\u0026plusmn;\u0026thinsp;2.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e23.15\u0026thinsp;\u0026plusmn;\u0026thinsp;2.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e23.78\u0026thinsp;\u0026plusmn;\u0026thinsp;3.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e23.77\u0026thinsp;\u0026plusmn;\u0026thinsp;3.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e23.74\u0026thinsp;\u0026plusmn;\u0026thinsp;3.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e19.09\u0026thinsp;\u0026plusmn;\u0026thinsp;3.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e18.95\u0026thinsp;\u0026plusmn;\u0026thinsp;3.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e19.06\u0026thinsp;\u0026plusmn;\u0026thinsp;3.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.93\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight middle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e8.85\u0026thinsp;\u0026plusmn;\u0026thinsp;2.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e8.95\u0026thinsp;\u0026plusmn;\u0026thinsp;2.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e8.96\u0026thinsp;\u0026plusmn;\u0026thinsp;2.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e25.12\u0026thinsp;\u0026plusmn;\u0026thinsp;3.33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e25.13\u0026thinsp;\u0026plusmn;\u0026thinsp;3.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e25.09\u0026thinsp;\u0026plusmn;\u0026thinsp;3.17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eVentilation region volume proportion (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHyper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2.72\u0026thinsp;\u0026plusmn;\u0026thinsp;4.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2.83\u0026thinsp;\u0026plusmn;\u0026thinsp;4.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.83\u0026thinsp;\u0026plusmn;\u0026thinsp;4.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e93.75\u0026thinsp;\u0026plusmn;\u0026thinsp;4.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e93.18\u0026thinsp;\u0026plusmn;\u0026thinsp;4.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e93.15\u0026thinsp;\u0026plusmn;\u0026thinsp;5.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.44\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.40\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePoor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2.59\u0026thinsp;\u0026plusmn;\u0026thinsp;2.33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2.97\u0026thinsp;\u0026plusmn;\u0026thinsp;2.16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e3.00\u0026thinsp;\u0026plusmn;\u0026thinsp;2.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.94\u0026thinsp;\u0026plusmn;\u0026thinsp;0.81\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.02\u0026thinsp;\u0026plusmn;\u0026thinsp;0.76\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.02\u0026thinsp;\u0026plusmn;\u0026thinsp;0.82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eVentilation region weight proportion (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHyper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.53\u0026thinsp;\u0026plusmn;\u0026thinsp;1.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.55\u0026thinsp;\u0026plusmn;\u0026thinsp;1.24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.55\u0026thinsp;\u0026plusmn;\u0026thinsp;1.18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e1.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e85.52\u0026thinsp;\u0026plusmn;\u0026thinsp;7.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e83.90\u0026thinsp;\u0026plusmn;\u0026thinsp;6.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e84.06\u0026thinsp;\u0026plusmn;\u0026thinsp;7.21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e0.04\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePoor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e8.82\u0026thinsp;\u0026plusmn;\u0026thinsp;4.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e10.06\u0026thinsp;\u0026plusmn;\u0026thinsp;4.24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e9.98\u0026thinsp;\u0026plusmn;\u0026thinsp;4.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u003cb\u003e0.01\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u003cb\u003e0.02\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e5.12\u0026thinsp;\u0026plusmn;\u0026thinsp;3.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e5.48\u0026thinsp;\u0026plusmn;\u0026thinsp;3.18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e5.42\u0026thinsp;\u0026plusmn;\u0026thinsp;3.34\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.98\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\u003e3.3 Correlation Between TUE and VUE Metrics\u003c/h2\u003e\u003cp\u003eCorrelation analyses among TUE, AP-VUE, and VP-VUE datasets revealed statistically significant correlations (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). Specifically, the comparison between TUE and AP-VUE showed correlation coefficients of 0.97 for total lung volume and 0.99 for total lung weight. The volume proportions and weight proportions of individual lung lobes exhibited correlation coefficients ranging from 0.97 to 0.99. For the four ventilation regions, the volume proportions correlated between 0.83 and 0.98, while the weight proportions ranged from 0.75 to 0.98. Similarly, comparison between AP-VUE and VP-VUE yielded correlation coefficients of 0.98 for total lung volume and 0.99 for total volume weight. The relative volume and weight proportions of lung lobes ranged from 0.98 to 0.99, and the volume and weight proportions of the four ventilation regions exhibited correlation coefficients of 0.92\u0026ndash;0.99 and 0.90\u0026ndash;0.99, respectively. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e illustrates the correlation comparisons of volume and weight proportions of lung lobes and ventilation regions among TUE, AP-VUE, and VP-VUE. Detailed correlation values are provided in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\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\u003eCorrelation Between TUE and VUE.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eItems\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eTUE vs VUEA\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eTUE vs VUEV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c7\" namest=\"c6\"\u003e\u003cp\u003eVUEA vs VUEV\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePearson Corr\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003ePearson Corr\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003ePearson Corr\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003evolume total (mL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eweight total (g)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLobe relative volume (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight middle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLobe relative weight (%)\u003c/b\u003e\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\u003eLeft upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight middle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eVentilation region volume proportion (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHyper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.97\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePoor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eVentilation region weight proportion (%)\u003c/b\u003e\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\u003eHyper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePoor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.92\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.76\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;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=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003e3.4 Bias and MAPE Between TUE and VUE\u003c/h2\u003e\u003cp\u003eThe biases of total lung volume calculated by comparing TUE with AP-VUE and VP-VUE were \u0026minus;\u0026thinsp;98.11 mL and \u0026minus;\u0026thinsp;95.27 mL, respectively, while the biases for total lung weight were \u0026minus;\u0026thinsp;17.39 g and \u0026minus;\u0026thinsp;10.14 g, respectively. The MAPEs for total lung volume were 2.37% and 2.15%, and for total lung weight were 1.80% and 0.89%, respectively. When comparing TUE with VUE, the biases of relative volume and weight proportions for each lung lobe ranged from \u0026minus;\u0026thinsp;0.18 to +\u0026thinsp;0.18, with corresponding MAPEs between 0.00% and 1.90%. For the ventilation regions, volume proportion biases ranged from \u0026minus;\u0026thinsp;0.60 to 0.41, and weight proportion biases ranged from \u0026minus;\u0026thinsp;1.62 to 1.23. The normal ventilation region exhibited the lowest MAPE values for volume proportion at 0.60% and 0.64%, whereas MAPE values for other ventilation regions exceeded 10%. Similarly, the weight proportion MAPE for the normal ventilation region was lowest at 1.74% and 1.63%, with other regions showing MAPE values above 11%. Detailed bias and MAPE values for the relative volume and weight proportions of lung lobes and the four ventilation regions are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\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\u003eComparison of Bias and MAPE Across TUE, AP-VUE, and VP-VUE.\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=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eItems\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eBias vs TUE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e\u003cp\u003eMAPE vs TUE\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAP-VUE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eVP-VUE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAP-VUE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eVP-VUE\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003evolume total (mL)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-98.11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-95.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.37%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e2.15%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eweight total (g)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-17.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-10.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.80%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.89%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"5\" nameend=\"c5\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLobe relative volume (%)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.54%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.29%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.73%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.48%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.02%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.19%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight middle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.77%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.90%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.32%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.22%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLobe relative weight (%)\u003c/b\u003e\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\u003eLeft upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.04\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.21%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.00%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLeft lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.11%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.01%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight upper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.85%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.21%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight middle\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.28%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.35%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRight lower\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.18%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.04%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eVentilation region volume proportion (%)\u003c/b\u003e\u003c/p\u003e\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\u003eHyper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e10.87%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e10.46%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-0.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.60%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.64%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePoor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e24.09%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e23.65%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e21.24%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e19.24%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e\u003cp\u003e\u003cb\u003eVentilation region weight proportion (%)\u003c/b\u003e\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\u003eHyper\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.02\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e12.33%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12.63%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e-1.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-1.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.74%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.63%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePoor\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.23\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e1.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e18.99%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e17.18%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNon\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.36\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e14.35%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11.50%\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":"4. Discussion","content":"\u003cp\u003eThe results of this study demonstrated no significant differences in total lung volume/weight, volume/weight proportions of individual lobes, or volume proportions of ventilation regions (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). However, some significant differences were observed in the weight proportions of specific ventilation regions (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). The correlation coefficients between TUE and both AP-VUE and VP-VUE ranged from 0.75 to 0.99. Except for the volume and weight proportions of the hyperventilated, normal, and non-ventilation regions, the maximum MAPE between parameters calculated from TUE and those from VUE images was 2.15%.\u003c/p\u003e\u003cp\u003eThe virtual unenhanced imaging technology based on dual-energy CT utilizes a material decomposition algorithm to eliminate the influence of iodinated contrast from enhanced images, thereby generating unenhanced, iodine-free images that resemble conventional unenhanced CT scans. These VUE images have demonstrated potential as a feasible alternative to traditional TUE \u003csup\u003e(\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e)\u003c/sup\u003e. Concurrently, the advancement of artificial intelligence has ushered lung CT segmentation into an era of precision quantification analysis. Prominent deep learning architectures, such as U-Net\u003csup\u003e(\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e)\u003c/sup\u003e and LDD-Net \u003csup\u003e(\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e)\u003c/sup\u003e, have markedly improved segmentation accuracy, providing a technical foundations for multiparametric quantitative analysis of pulmonary tissues. In this study, an enhanced VB-Net model was implemented via the uRP medical image analysis platform. This model incorporates a bottleneck architecture and multi-resolution optimization strategies to achieve automated segmentation of pulmonary lobes (right upper, middle, lower; left upper, lower) across three types of images: TUE, AP-VUE, and VP-VUE. A systematic quantitative analysis was subsequently performed on lobar volume and weight proportions, as well as ventilation function parameters (normalized to total lung volume and expressed as percentages).\u003c/p\u003e\u003cp\u003eQuantitative CT analysis revealed statistically significant differences in lobar weight proportions between TUE and AP-VUE scans within both normal ventilation regions (85.52%\u0026plusmn;7.06% vs 83.90%\u0026plusmn;6.89%) and low-ventilation regions (8.82%\u0026plusmn;4.43% vs 10.06%\u0026plusmn;4.24%) (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05), with AP-VUE collectively accounting for approximately 93% of total pulmonary weight. Notably, the low-ventilation weight proportions in TUE scans (8.82%\u0026plusmn;4.43%) was significantly lower than that observed in VP-VUE (9.98%\u0026plusmn;4.47%, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). This discrepancy may be attributed to residual iodine interference during AP-VUE reconstruction, caused by elevated contrast concentration in the arterial phase, potentially leading to distorted functional assessments in the \u0026minus;\u0026thinsp;950~-100 HU range. Conversely, the reduced iodine concentration in VP-VUE enabled effective artifact suppression within a narrower \u0026minus;\u0026thinsp;500~-100 HU window (10.2% of total lung volume), in line with quantitative artifact analyses by Okada et al. \u003csup\u003e(\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e)\u003c/sup\u003e. In a methodological innovation, this study employed deep learning-based lobar segmentation to generate difference maps of CT attenuations (-950~-500 HU) between VUE and TUE scans, providing critical anatomical insights for optimizing multiphase pulmonary CT protocols. Intriguingly. Interestingly, VP-VUE showed discrepancies from TUE only in minimal proportion of non-ventilated regions (accounting for 4.8% of total volume), further supporting its superior approximation of TUE relative to AP-VUE from a segmentation-based perspective. This finding aligns with the CT attenuation-based validation of virtual non-contrast techniques by Guo et al. \u003csup\u003e(\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e)\u003c/sup\u003e, confirming the higher fidelity of venous-phase over arterial-phase VUE reconstructions.\u003c/p\u003e\u003cp\u003eTUE exhibited high correlations coefficients with both AP/VP-VUE in terms of lobar volume and weight proportions as well as volumetric proportions across different ventilation regions (r\u0026thinsp;=\u0026thinsp;0.83\u0026ndash;0.99, \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). However, slightly lower correlations were observed for non-ventilated weight proportions (r\u0026thinsp;=\u0026thinsp;0.75\u0026ndash;0.76), which may be attributed to the limited representation of non-ventilated regions\u0026mdash;comprising only approximately 5% of total lung\u0026mdash;thereby increasing statistical variability. Bias analysis revealed narrow ranges (-0.60 to 0.41, all \u0026lt;\u0026thinsp;1) across lobar volume/weight proportions and ventilation region volumetric proportions. Notably, MAPE for normal ventilation regions were exceptionally low, measuring 0.60\u0026ndash;0.64% for volume (93% of total) and 1.63\u0026ndash;1.74% for weight (84% of total), indicating superior error control. The integration of TUE-based lobar segmentation techniques provides high-precision imaging data for pulmonary disease research, particularly in evaluating dominant regions (93% volume and 84% weight of normal ventilation regions).\u003c/p\u003e\u003cp\u003eAccurate lobar segmentation facilitates anatomically guided registration of individual pulmonary lobes by leveraging their functional independence, spatial isolation, and distinct respiratory kinematics. This methodological advancement substantially improves the precision of lesion localization, enhances the estimation of respiratory motion, and serves as a critical preprocessing step for advanced automated pulmonary image analysis. Conventional segmentation datasets primarily rely on unenhanced CT scans to avoid CT attenuation distortion caused by iodinated contrast agent. In this study, we integrated multiphase VUE imaging\u0026mdash;specifically AP- and VP-VUE\u0026mdash;with deep learning-based segmentation to assess the consistency of quantitative parameters across modalities. Using the uRP platform's fully automated multiparametric analysis\u0026mdash;including volume, density, CT attenuation distribution\u0026mdash;we demonstrated VUE provides quantitatively comparable results to TUE in dual-energy contrast-enhanced CT examinations. Clinically, the combination of dual-phase enhancement with VUE reconstruction resulted in a 35.70% reduction in radiation dose reduction compared to conventional triphasic imaging protocols (mean ED: 2.85 vs 4.43 mSv), aligning with radiation optimization benchmarks proposed by Strotzer et al. \u003csup\u003e(\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e)\u003c/sup\u003e. These findings offer strong support for the adoption of radiation-efficient enhanced-only imaging protocols without compromising the quantitative diagnostic capacity.\u003c/p\u003e\u003cp\u003eConventional spirometry suffers from several inherent limitations in pulmonary function assessment, including a high dependency on patient cooperation, considerable measurement variability, and an inability to evaluate function at the lobar or segmental level, thereby restricting its application to whole-lung assessments\u003csup\u003e(\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e)\u003c/sup\u003e.Prior studies\u003csup\u003e(\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e)\u003c/sup\u003e have demonstrated that quantitative analysis of unenhanced CT data enables accurate measurement of emphysematous volume and weight changes in COPD, facilitating the differentiation of emphysematous, functional, and interstitial lung tissues through visualized regional assessment. CT attenuation-based tissue segmentation provides enhanced accuracy in quantifying quantitative parameters across heterogeneous ventilation regions, thereby enhancing the comprehensive and precise evaluation of pulmonary pathologies\u003csup\u003e(\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e)\u003c/sup\u003e. Building on this foundations, our study integrates multiphase VUE imaging with deep learning segmentation to reveal that virtual enhanced images derived from different enhancement phases exert phase-dependent influences on weight proportions distribution across ventilation regions. This phase-related variation underscores the need for careful consideration in clinical settings, particularly when selecting optimized imaging protocols tailored to specific pulmonary disease assessment.\u003c/p\u003e\u003cp\u003eThis study acknowledges three primary technical limitations within its validation framework: (1) The absence of a systematic comparison between enhanced CT-based segmentation algorithms and gold-standard unenhanced imaging, particularly in assessing the generalizability of deep learning models across different CT scanner vendors; (2) The current analysis of spatial heterogeneity using VUE technology is limited to the lobar level and lacks evaluation at the subsegmental anatomical scale, which may provide additional insights related to bronchial anatomical variations and regional hemodynamic characteristics; (3) The functional validation framework does not incorporate multimodal correlation analysis between dynamic pulmonary function parameters (e.g., DLCO, FEV1) and CT-derived quantitative indices (e.g., low-ventilation volume proportion), and is further constrained by the absence of longitudinal validation data under exercise-induced stress conditions.\u003c/p\u003e\u003cp\u003eIn conclusion, within a deep learning-based automated lobar segmentation framework, VP-VUE and conventional TUE imaging demonstrated high concordance in key anatomical and functional evaluation metrics. However, the observed differences in low-ventilation distribution characteristics highlight the need for clinical attention when selecting imaging modalities for functional pulmonary assessment.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have reviewed the manuscript and approve to submit to your journal. (Chao Zou, Jun Hu, An Yan, Aiyun Sun, Wen Yang, Xin Peng, Xu Yang , Shangwen Yang, and Xiaoyan Xin).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWriting \u0026ndash; Original Draft Preparation: Chao Zou, Jun Hu, An Yan. Data Curation \u0026amp; Formal Analysis: Aiyun Sun, Wen Yang, Xin Peng, Xu Yang. Writing \u0026ndash; Review \u0026amp; Editing: Shangwen Yang, Xiaoyan Xin. All authors reviewed and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFUNDING\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported in part by fundings for Clinical Trials from the Affiliated Drum Tower Hospital, Medical School of Nanjing University (2023-LCYJ-PY-26) ，Nanjing health science and technology development special fund major project (ZKX22015)，and Key Projects for the Development of New Medical Technologies from the Affiliated Drum Tower Hospital, Medical School of Nanjing University (XJSFZLX202313).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data that support the findings of this study are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the Medical Ethics Committee of the Nanjing Drum Tower Hospital (Approval No:2022-449-02).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics declaration\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was conducted in accordance with the \u0026ldquo;Declaration of Helsinki\u0026rdquo;.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to participate\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe need for informed consent was waived due to the retrospective nature of the study.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to publish\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have agreed to the submission of this manuscript for publication. Furthermore, the authors declare that there are no conflicts of interest related to the publication of this manuscript.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003ede Margerie-Mellon C, Chassagnon G. Artificial intelligence: A critical review of applications for lung nodule and lung cancer. Diagn Interv Imaging. 2023;104(1):11\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSteinhardt M, Marka AW, Ziegelmayer S, Makowski M, Braren R, Graf M et al. Comparison of Virtual Non-Contrast and True Non-Contrast CT Images Obtained by Dual-Layer Spectral CT in COPD Patients. Bioengineering. 2024;11(4).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMeyer KC. Pulmonary fibrosis, part I: epidemiology, pathogenesis, and diagnosis. Expert Rev Respir Med. 2017:1\u0026ndash;17.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCoppadoro A, Leiser P, Kirschning T, Wei\u0026szlig; C, Hagmann M, Schoettler J et al. A quantitative CT parameter for the assessment of pulmonary oedema in patients with acute respiratory distress syndrome. PLoS ONE. 2020;15(11).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBernsen MLE, Veendrick PB, Martens JM, Pijl MEJ, Hofmeijer J, van Gorp MJ. Initial experience with dual-layer detector spectral CT for diagnosis of blood or contrast after endovascular treatment for ischemic stroke. Neuroradiology. 2021;64(1):69\u0026ndash;76.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePark A, Lee YH, Seo HS. Could both intrinsic and extrinsic iodine be successfully suppressed on virtual non-contrast CT images for detecting thyroid calcification? Japanese J Radiol. 2021;39(6):580\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRajiah P, Parakh A, Kay F, Baruah D, Kambadakone AR, Leng S. Update on Multienergy CT: Physics, Principles, and Applications. Radiographics. 2020;40(5):1284\u0026ndash;308.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZeng W, Tang J, Xu X, Zhang Y, Zeng L, Zhang Y, et al. Safety of non-ionic contrast media in CT examinations for out-patients: retrospective multicenter analysis of 473,482 patients. Eur Radiol. 2024;34(9):5570\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWu J, Xia Y, Wang X, Wei Y, Liu A, Innanje A et al. uRP: An integrated research platform for one-stop analysis of medical images. Front Radiol. 2023;3.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDixon AK. Benefits and costs, an eternal balance. Ann ICRP. 2007;37(1):1\u0026ndash;3.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJungblut L, Sartoretti T, Kronenberg D, Mergen V, Euler A, Schmidt B et al. Performance of virtual non-contrast images generated on clinical photon-counting detector CT for emphysema quantification: proof of concept. Br J Radiol. 2022;95(1135).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWong WD, Mohammed MF, Nicolaou S, Schmiedeskamp H, Khosa F, Murray N, et al. Impact of Dual-Energy CT in the Emergency Department: Increased Radiologist Confidence, Reduced Need for Follow-Up Imaging, and Projected Cost Benefit. Am J Roentgenol. 2020;215(6):1528\u0026ndash;38.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKumari KS, Samal S, Mishra R, Madiraju G, Mahabob MN, Shivappa AB. Diagnosing COVID-19 from CT Image of Lung Segmentation \u0026amp; Classification with Deep Learning Based on Convolutional Neural Networks. Wireless Pers Commun. 2021;127(3):2483\u0026ndash;99.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEl-Bana S, Al-Kabbany A, Sharkas M. A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans. Diagnostics. 2020;10(3).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOkada K, Matsuda M, Tsuda T, Kido T, Murata A, Nishiyama H, et al. Dual-energy computed tomography for evaluation of breast cancer: value of virtual monoenergetic images reconstructed with a noise-reduced monoenergetic reconstruction algorithm. Japanese J Radiol. 2019;38(2):154\u0026ndash;64.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGuo Y, Fan Q, Ren Z, Yu N, Tan H, Ma G. Feasibility of replacing true non-contrast images with virtual non-contrast images in quantitative analysis of emphysema. Die Radiol. 2025.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eStrotzer QD, Schachner C, Scheuermeyer L, Raab F, Meiler S, Malfertheiner MV et al. Quantitative chest computed tomography: regional differences in dual-energy-derived virtual vs. true non-contrast scans. Clin Radiol. 2025;85.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCornelius T. Clinical guideline highlights for the hospitalist: GOLD COPD update 2024. J Hosp Med. 2024;19(9):818\u0026ndash;20.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eden Harder AM, Bangert F, van Hamersvelt RW, Leiner T, Milles J, Schilham AMR, et al. The Effects of Iodine Attenuation on Pulmonary Nodule Volumetry using Novel Dual-Layer Computed Tomography Reconstructions. Eur Radiol. 2017;27(12):5244\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eUfuk F, Demirci M, Altinisik G, Karasu U. Quantitative analysis of Sjogren's syndrome related interstitial lung disease with different methods. Eur J Radiol. 2020;128.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhang G, Jiang S, Yang Z, Gong L, Ma X, Zhou Z, et al. Automatic nodule detection for lung cancer in CT images: A review. Comput Biol Med. 2018;103:287\u0026ndash;300.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"dual-energy CT, lung lobar segmentation, artificial intelligence, Deep learning, virtual unenhanced images, true unenhanced images","lastPublishedDoi":"10.21203/rs.3.rs-7300980/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7300980/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003eObjective\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eTo evaluate the feasibility of applying deep learning-based automatic lung segmentation to virtual unenhanced (VUE) images generated from gemstone spectral imaging (GSI) CT scans.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMaterials and Methods\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eThis retrospective study included patients who underwent chest CT scans. The protocol consisted of conventional true unenhanced (TUE) scans, arterial-phase (AP) GSI-enhanced scans, and venous-phase (VP) GSI-enhanced scans. VUE images were reconstructed from both enhanced phases. A deep neural network was utilized to automatically segment lung lobes and calculate total lung volume, weight and relative fractions, as well as the volume and weight fractions of regions with different ventilation functionality. Differences among the three image sets, as well as their correlations, bias, and mean absolute percentage error (MAPE), were assessed.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eA total of 223 patients were enrolled. Statistically significant differences were observed between TUE and AP-VUE in the weight fractions of normally ventilated regions, and between TUE and both AP-VUE and VP-VUE in the weight fractions of poorly ventilated regions (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). No significant differences were found among the three image types in other segmentation parameters (all \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05). The correlation coefficients of non-ventilated region weight fractions between AP-VUE and TUE, and between VP-VUE and TUE, were 0.75 and 0.76, respectively; all other correlation coefficients exceeded 0.80. Bias values for lobar and functional region volume and weight fractions ranged from \u0026minus;\u0026thinsp;1.62 to 1.23, while MAPE ranged from 0.00\u0026ndash;2.37%. Compared to three-phase scanning, dual-phase enhanced scanning without TUE resulted in a 35.70% reduction in radiation dose.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusion\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eLung parameters calculated from VUE images using deep learning-based segmentation demonstrated strong agreement with those derived from TUE, with minimal differences, high correlation, and low bias and MAPE.\u003c/p\u003e","manuscriptTitle":"Feasibility of Automated Accurate Lung Segmentation Using Deep Learning on Virtual Unenhanced Images from Gemstone Spectral CT Imaging For Pulmonary Ventilation Assessment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-30 07:25:22","doi":"10.21203/rs.3.rs-7300980/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2025-10-29T16:37:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"166818095862327366767389054847212171186","date":"2025-10-27T21:21:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"338535782570217649743462661936998153437","date":"2025-09-18T18:48:16+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-18T13:08:32+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-02T09:01:55+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-08T11:27:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-08T11:26:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2025-08-05T13:02:42+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b08a9472-320c-40b5-9db2-7fbd1e6752dc","owner":[],"postedDate":"September 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-09-30T07:25:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-30 07:25:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7300980","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7300980","identity":"rs-7300980","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}