Treffer: Preoperative Assessment of Extraprostatic Extension in Prostate Cancer Using an Interpretable Tabular Prior-Data Fitted Network-Based Radiomics Model From MRI.
Title:
Preoperative Assessment of Extraprostatic Extension in Prostate Cancer Using an Interpretable Tabular Prior-Data Fitted Network-Based Radiomics Model From MRI.
Authors:
Liu BC; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Ding XH; Department of Pathology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Xu HH; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Bai X; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Zhang XJ; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Cui MQ; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Guo AT; Department of Pathology, Third Medical Center of Chinese PLA General Hospital, Beijing, China., Mu XT; Department of Radiology, Third Medical Center of Chinese PLA General Hospital, Beijing, China., Xie LZ; GE Healthcare, MR Research China, Beijing, China., Kang HH; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Zhou SP; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China., Zhao J; Department of Radiology, Second Medical Center of Chinese PLA General Hospital, Beijing, China., Wang BJ; Department of Urology, Third Medical Center of Chinese PLA General Hospital, Beijing, China., Wang HY; Department of Radiology, First Medical Center, Chinese PLA General Hospital, Beijing, China.
Source:
Journal of magnetic resonance imaging : JMRI [J Magn Reson Imaging] 2026 Jan; Vol. 63 (1), pp. 98-112. Date of Electronic Publication: 2025 Sep 05.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Wiley-Liss Country of Publication: United States NLM ID: 9105850 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1522-2586 (Electronic) Linking ISSN: 10531807 NLM ISO Abbreviation: J Magn Reson Imaging Subsets: MEDLINE
Imprint Name(s):
Publication: <2005-> : Hoboken , N.J. : Wiley-Liss
Original Publication: Chicago, IL : Society for Magnetic Resonance Imaging, c1991-
Original Publication: Chicago, IL : Society for Magnetic Resonance Imaging, c1991-
MeSH Terms:
Prostatic Neoplasms*/diagnostic imaging , Prostatic Neoplasms*/pathology , Prostatic Neoplasms*/surgery , Magnetic Resonance Imaging*/methods , Image Interpretation, Computer-Assisted*/methods, Humans ; Male ; Aged ; Retrospective Studies ; Middle Aged ; Prostate/diagnostic imaging ; Prostate/pathology ; Prostatectomy ; Reproducibility of Results ; Preoperative Care ; Image Processing, Computer-Assisted/methods ; Algorithms ; ROC Curve ; Radiomics
References:
R. L. Siegel, T. B. Kratzer, A. N. Giaquinto, H. Sung, and A. Jemal, “Cancer Statistics, 2025,” CA: A Cancer Journal for Clinicians 75 (2025): 10–45.
T. M. Wheeler, O. Dillioglugil, M. W. Kattan, et al., “Clinical and Pathological Significance of the Level and Extent of Capsular Invasion in Clinical Stage T1‐2 Prostate Cancer,” Human Pathology 29 (1998): 856–862.
L. N. Nguyen, L. Head, K. Witiuk, et al., “The Risks and Benefits of Cavernous Neurovascular Bundle Sparing During Radical Prostatectomy: A Systematic Review and Meta‐Analysis,” Journal of Urology 198 (2017): 760–769.
L. Kayat Bittencourt, G. Litjens, C. A. Hulsbergen‐van de Kaa, B. Turkbey, E. L. Gasparetto, and J. O. Barentsz, “Prostate Cancer: The European Society of Urogenital Radiology Prostate Imaging Reporting and Data System Criteria for Predicting Extraprostatic Extension by Using 3‐T Multiparametric MR Imaging,” Radiology 276 (2015): 479–489.
S. Mehralivand, J. H. Shih, S. Harmon, et al., “A Grading System for the Assessment of Risk of Extraprostatic Extension of Prostate Cancer at Multiparametric MRI,” Radiology 290 (2019): 709–719.
K. J. Park, M.‐H. Kim, and J. K. Kim, “Extraprostatic Tumor Extension: Comparison of Preoperative Multiparametric MRI Criteria and Histopathologic Correlation After Radical Prostatectomy,” Radiology 296 (2020): 87–95.
U. Bansal, A. Estevez, J. Black, et al., “How Can We Identify Extraprostatic Extension (EPE) Before Surgery? The Use of a Preoperative Prostate MRI EPE Scoring System to Assess Postprostatectomy Locally Advanced Prostate Cancer,” Journal of Endourology 38 (2024): 499–504.
A. Ponsiglione, M. Gambardella, A. Stanzione, et al., “Radiomics for the Identification of Extraprostatic Extension With Prostate MRI: A Systematic Review and Meta‐Analysis,” European Radiology 34 (2023): 3981–3991.
A. Guerra, H. Wang, M. R. Orton, et al., “Prediction of Extracapsular Extension of Prostate Cancer by MRI Radiomic Signature: A Systematic Review,” Insights Into Imaging 15 (2024): 217.
R. Cuocolo, A. Stanzione, R. Faletti, et al., “MRI Index Lesion Radiomics and Machine Learning for Detection of Extraprostatic Extension of Disease: A Multicenter Study,” European Radiology 31 (2021): 7575–7583.
H. Bai, W. Xia, X. Ji, et al., “Multiparametric Magnetic Resonance Imaging‐Based Peritumoral Radiomics for Preoperative Prediction of the Presence of Extracapsular Extension With Prostate Cancer,” Journal of Magnetic Resonance Imaging 54 (2021): 1222–1230.
Y. Hou, Y.‐H. Zhang, J. Bao, et al., “Artificial Intelligence Is a Promising Prospect for the Detection of Prostate Cancer Extracapsular Extension With mpMRI: A Two‐Center Comparative Study,” European Journal of Nuclear Medicine and Molecular Imaging 48 (2021): 3805–3816.
M. Paschali, Z. Chen, L. Blankemeier, et al., “Foundation Models in Radiology: What, How, Why, and Why Not,” Radiology 314 (2025): e240597.
N. Hollmann, S. Müller, L. Purucker, et al., “Accurate Predictions on Small Data With a Tabular Foundation Model,” Nature 637 (2025): 319–326.
B. Turkbey, A. B. Rosenkrantz, M. A. Haider, et al., “Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2,” European Urology 76 (2019): 340–351.
G. J. L. H. van Leenders, T. H. van der Kwast, D. J. Grignon, et al., “The 2019 International Society of Urological Pathology (ISUP) Consensus Conference on Grading of Prostatic Carcinoma,” American Journal of Surgical Pathology 44 (2020): e87–e99.
H. Peng, F. Long, and C. Ding, “Feature Selection Based on Mutual Information: Criteria of Max‐Dependency, Max‐Relevance, and Min‐Redundancy,” IEEE Transactions on Pattern Analysis and Machine Intelligence 27 (2005): 1226–1238.
S. M. Lundberg and S.‐I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS) (Curran Associates Inc, 2017), 4768–4777.
M. Gatti, R. Faletti, F. Gentile, et al., “mEPE‐Score: A Comprehensive Grading System for Predicting Pathologic Extraprostatic Extension of Prostate Cancer at Multiparametric Magnetic Resonance Imaging,” European Radiology 32 (2022): 4942–4953.
A. B. Rosenkrantz, A. K. Shanbhogue, A. Wang, M. X. Kong, J. S. Babb, and S. S. Taneja, “Length of Capsular Contact for Diagnosing Extraprostatic Extension on Prostate MRI: Assessment at an Optimal Threshold,” Journal of Magnetic Resonance Imaging 43 (2016): 990–997.
J. R. Landis and G. G. Koch, “The Measurement of Observer Agreement for Categorical Data,” Biometrics 33 (1977): 159–174.
J. C. C. Kwong, A. Khondker, E. Meng, et al., “Development, Multi‐Institutional External Validation, and Algorithmic Audit of an Artificial Intelligence‐Based Side‐Specific Extra‐Prostatic Extension Risk Assessment Tool (SEPERA) for Patients Undergoing Radical Prostatectomy: A Retrospective Cohort Study,” Lancet Digital Health 5 (2023): e435–e445.
J. G. Heetman, T. F. W. Soeterik, L. Wever, et al., “A Side‐Specific Nomogram for Extraprostatic Extension May Reduce the Positive Surgical Margin Rate in Radical Prostatectomy,” World Journal of Urology 40 (2022): 2919–2924.
D. A. Bluemke, L. Moy, M. A. Bredella, et al., “Assessing Radiology Research on Artificial Intelligence: A Brief Guide for Authors, Reviewers, and Readers‐From the Radiology Editorial Board,” Radiology 294 (2020): 487–489.
J. Pearl, “Causality: Models, Reasoning, and Inference (second edition). Cambridge University Press, 2000,” Econometric Theory 19 (2003): 675–685.
J. Lever, M. Krzywinski, and N. Altman, “Model Selection and Overfitting,” Nature Methods 13 (2016): 703–704.
R. J. Gillies, P. E. Kinahan, and H. Hricak, “Radiomics: Images Are More Than Pictures, They Are Data,” Radiology 278 (2016): 563–577.
P. Lambin, R. T. H. Leijenaar, T. M. Deist, et al., “Radiomics: The Bridge Between Medical Imaging and Personalized Medicine,” Nature Reviews. Clinical Oncology 14 (2017): 749–762.
A. Wibmer, H. A. Vargas, T. F. Donahue, et al., “Diagnosis of Extracapsular Extension of Prostate Cancer on Prostate MRI: Impact of Second‐Opinion Readings by Subspecialized Genitourinary Oncologic Radiologists,” AJR. American Journal of Roentgenology 205 (2015): W73–W78.
M. H. Choi, D. H. Kim, Y. J. Lee, S. E. Rha, and J. Y. Lee, “Imaging Features of the PI‐RADS for Predicting Extraprostatic Extension of Prostate Cancer: Systematic Review and Meta‐Analysis,” Insights Into Imaging 14 (2023): 77.
T. M. Wheeler, O. Dillioglugil, M. W. Kattan, et al., “Clinical and Pathological Significance of the Level and Extent of Capsular Invasion in Clinical Stage T1‐2 Prostate Cancer,” Human Pathology 29 (1998): 856–862.
L. N. Nguyen, L. Head, K. Witiuk, et al., “The Risks and Benefits of Cavernous Neurovascular Bundle Sparing During Radical Prostatectomy: A Systematic Review and Meta‐Analysis,” Journal of Urology 198 (2017): 760–769.
L. Kayat Bittencourt, G. Litjens, C. A. Hulsbergen‐van de Kaa, B. Turkbey, E. L. Gasparetto, and J. O. Barentsz, “Prostate Cancer: The European Society of Urogenital Radiology Prostate Imaging Reporting and Data System Criteria for Predicting Extraprostatic Extension by Using 3‐T Multiparametric MR Imaging,” Radiology 276 (2015): 479–489.
S. Mehralivand, J. H. Shih, S. Harmon, et al., “A Grading System for the Assessment of Risk of Extraprostatic Extension of Prostate Cancer at Multiparametric MRI,” Radiology 290 (2019): 709–719.
K. J. Park, M.‐H. Kim, and J. K. Kim, “Extraprostatic Tumor Extension: Comparison of Preoperative Multiparametric MRI Criteria and Histopathologic Correlation After Radical Prostatectomy,” Radiology 296 (2020): 87–95.
U. Bansal, A. Estevez, J. Black, et al., “How Can We Identify Extraprostatic Extension (EPE) Before Surgery? The Use of a Preoperative Prostate MRI EPE Scoring System to Assess Postprostatectomy Locally Advanced Prostate Cancer,” Journal of Endourology 38 (2024): 499–504.
A. Ponsiglione, M. Gambardella, A. Stanzione, et al., “Radiomics for the Identification of Extraprostatic Extension With Prostate MRI: A Systematic Review and Meta‐Analysis,” European Radiology 34 (2023): 3981–3991.
A. Guerra, H. Wang, M. R. Orton, et al., “Prediction of Extracapsular Extension of Prostate Cancer by MRI Radiomic Signature: A Systematic Review,” Insights Into Imaging 15 (2024): 217.
R. Cuocolo, A. Stanzione, R. Faletti, et al., “MRI Index Lesion Radiomics and Machine Learning for Detection of Extraprostatic Extension of Disease: A Multicenter Study,” European Radiology 31 (2021): 7575–7583.
H. Bai, W. Xia, X. Ji, et al., “Multiparametric Magnetic Resonance Imaging‐Based Peritumoral Radiomics for Preoperative Prediction of the Presence of Extracapsular Extension With Prostate Cancer,” Journal of Magnetic Resonance Imaging 54 (2021): 1222–1230.
Y. Hou, Y.‐H. Zhang, J. Bao, et al., “Artificial Intelligence Is a Promising Prospect for the Detection of Prostate Cancer Extracapsular Extension With mpMRI: A Two‐Center Comparative Study,” European Journal of Nuclear Medicine and Molecular Imaging 48 (2021): 3805–3816.
M. Paschali, Z. Chen, L. Blankemeier, et al., “Foundation Models in Radiology: What, How, Why, and Why Not,” Radiology 314 (2025): e240597.
N. Hollmann, S. Müller, L. Purucker, et al., “Accurate Predictions on Small Data With a Tabular Foundation Model,” Nature 637 (2025): 319–326.
B. Turkbey, A. B. Rosenkrantz, M. A. Haider, et al., “Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2,” European Urology 76 (2019): 340–351.
G. J. L. H. van Leenders, T. H. van der Kwast, D. J. Grignon, et al., “The 2019 International Society of Urological Pathology (ISUP) Consensus Conference on Grading of Prostatic Carcinoma,” American Journal of Surgical Pathology 44 (2020): e87–e99.
H. Peng, F. Long, and C. Ding, “Feature Selection Based on Mutual Information: Criteria of Max‐Dependency, Max‐Relevance, and Min‐Redundancy,” IEEE Transactions on Pattern Analysis and Machine Intelligence 27 (2005): 1226–1238.
S. M. Lundberg and S.‐I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS) (Curran Associates Inc, 2017), 4768–4777.
M. Gatti, R. Faletti, F. Gentile, et al., “mEPE‐Score: A Comprehensive Grading System for Predicting Pathologic Extraprostatic Extension of Prostate Cancer at Multiparametric Magnetic Resonance Imaging,” European Radiology 32 (2022): 4942–4953.
A. B. Rosenkrantz, A. K. Shanbhogue, A. Wang, M. X. Kong, J. S. Babb, and S. S. Taneja, “Length of Capsular Contact for Diagnosing Extraprostatic Extension on Prostate MRI: Assessment at an Optimal Threshold,” Journal of Magnetic Resonance Imaging 43 (2016): 990–997.
J. R. Landis and G. G. Koch, “The Measurement of Observer Agreement for Categorical Data,” Biometrics 33 (1977): 159–174.
J. C. C. Kwong, A. Khondker, E. Meng, et al., “Development, Multi‐Institutional External Validation, and Algorithmic Audit of an Artificial Intelligence‐Based Side‐Specific Extra‐Prostatic Extension Risk Assessment Tool (SEPERA) for Patients Undergoing Radical Prostatectomy: A Retrospective Cohort Study,” Lancet Digital Health 5 (2023): e435–e445.
J. G. Heetman, T. F. W. Soeterik, L. Wever, et al., “A Side‐Specific Nomogram for Extraprostatic Extension May Reduce the Positive Surgical Margin Rate in Radical Prostatectomy,” World Journal of Urology 40 (2022): 2919–2924.
D. A. Bluemke, L. Moy, M. A. Bredella, et al., “Assessing Radiology Research on Artificial Intelligence: A Brief Guide for Authors, Reviewers, and Readers‐From the Radiology Editorial Board,” Radiology 294 (2020): 487–489.
J. Pearl, “Causality: Models, Reasoning, and Inference (second edition). Cambridge University Press, 2000,” Econometric Theory 19 (2003): 675–685.
J. Lever, M. Krzywinski, and N. Altman, “Model Selection and Overfitting,” Nature Methods 13 (2016): 703–704.
R. J. Gillies, P. E. Kinahan, and H. Hricak, “Radiomics: Images Are More Than Pictures, They Are Data,” Radiology 278 (2016): 563–577.
P. Lambin, R. T. H. Leijenaar, T. M. Deist, et al., “Radiomics: The Bridge Between Medical Imaging and Personalized Medicine,” Nature Reviews. Clinical Oncology 14 (2017): 749–762.
A. Wibmer, H. A. Vargas, T. F. Donahue, et al., “Diagnosis of Extracapsular Extension of Prostate Cancer on Prostate MRI: Impact of Second‐Opinion Readings by Subspecialized Genitourinary Oncologic Radiologists,” AJR. American Journal of Roentgenology 205 (2015): W73–W78.
M. H. Choi, D. H. Kim, Y. J. Lee, S. E. Rha, and J. Y. Lee, “Imaging Features of the PI‐RADS for Predicting Extraprostatic Extension of Prostate Cancer: Systematic Review and Meta‐Analysis,” Insights Into Imaging 14 (2023): 77.
Grant Information:
82271951 National Natural Science Foundation of China; U24A20755 National Natural Science Foundation of China
Contributed Indexing:
Keywords: extraprostatic extension; foundation model; interpretability; magnetic resonance imaging; prostate cancer; radiomics; tabular prior‐data fitted network
Local Abstract: [plain-language-summary] MRI assessment for extraprostatic extension (EPE) of prostate cancer is challenging due to limited accuracy and interobserver agreement. This multicenter study develops a Tabular Prior‐data Fitted Network‐based radiomics model to evaluate EPE. The results demonstrate that the model performed well in both internal and external tests, and improved diagnostic accuracy and agreement when incorporating radiologists' interpretations, particularly benefiting less experienced radiologists. The proposed model may facilitate clinical assessment of EPE. This study explored the potential application of radiomics in EPE assessment, conducted modeling exploration based on a foundation model, and employed a novel approach incorporating radiologist assessment to enhance clinical utility.
Local Abstract: [plain-language-summary] MRI assessment for extraprostatic extension (EPE) of prostate cancer is challenging due to limited accuracy and interobserver agreement. This multicenter study develops a Tabular Prior‐data Fitted Network‐based radiomics model to evaluate EPE. The results demonstrate that the model performed well in both internal and external tests, and improved diagnostic accuracy and agreement when incorporating radiologists' interpretations, particularly benefiting less experienced radiologists. The proposed model may facilitate clinical assessment of EPE. This study explored the potential application of radiomics in EPE assessment, conducted modeling exploration based on a foundation model, and employed a novel approach incorporating radiologist assessment to enhance clinical utility.
Entry Date(s):
Date Created: 20250905 Date Completed: 20251216 Latest Revision: 20251216
Update Code:
20251216
DOI:
10.1002/jmri.70111
PMID:
40910573
Database:
MEDLINE
Weitere Informationen
Background: MRI assessment for extraprostatic extension (EPE) of prostate cancer (PCa) is challenging due to limited accuracy and interobserver agreement.
Purpose: To develop an interpretable Tabular Prior-data Fitted Network (TabPFN)-based radiomics model to evaluate EPE using MRI and explore its integration with radiologists' assessments.
Study Type: Retrospective.
Population: Five hundred and thirteen consecutive patients who underwent radical prostatectomy. Four hundred and eleven patients from center 1 (mean age 67 ± 7 years) formed training (287 patients) and internal test (124 patients) sets, and 102 patients from center 2 (mean age 66 ± 6 years) were assigned as an external test set.
Field Strength/sequence: Three Tesla, fast spin echo T2-weighted imaging (T2WI) and diffusion-weighted imaging using single-shot echo planar imaging.
Assessment: Radiomics features were extracted from T2WI and apparent diffusion coefficient maps, and the TabRadiomics model was developed using TabPFN. Three machine learning models served as baseline comparisons: support vector machine, random forest, and categorical boosting. Two radiologists (with > 1500 and > 500 prostate MRI interpretations, respectively) independently evaluated EPE grade on MRI. Artificial intelligence (AI)-modified EPE grading algorithms incorporating the TabRadiomics model with radiologists' interpretations of curvilinear contact length and frank EPE were simulated.
Statistical Tests: Receiver operating characteristic curve (AUC), Delong test, and McNemar test. p < 0.05 was considered significant.
Results: The TabRadiomics model performed comparably to machine learning models in both internal and external tests, with AUCs of 0.806 (95% CI, 0.727-0.884) and 0.842 (95% CI, 0.770-0.912), respectively. AI-modified algorithms showed significantly higher accuracies compared with the less experienced reader in internal testing, with up to 34.7% of interpretations requiring no radiologist input. However, no difference was observed in both readers in the external test set.
Data Conclusions: The TabRadiomics model demonstrated high performance in EPE assessment and may improve clinical assessment in PCa.
Evidence Level: 4.
Technical Efficacy: Stage 2.
(© 2025 International Society for Magnetic Resonance in Medicine.)