Development of a deep learning-based system for supporting medical decision-making in PI-RADs score determination

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

Aim: to explore the development of a computer-aided diagnosis (CAD) system based on deep learning (DL) neural networks aimed at minimizing human error in PI-RADS grading and supporting medical decision-making.

Materials and Methods. This retrospective multicenter study included a cohort of 136 patients, comprising 108 cases of PCa (PI-RADS score 4–5) and 28 cases of benign conditions (PI-RADS score 1–2). The 3D U-Net architecture was applied to process T2-weighted images (T2W), diffusion-weighted images (DWI), and dynamic contrast-enhanced images (DCE). Statistical analysis was conducted using Python libraries to assess diagnostic performance, including sensitivity, specificity, Dice similarity coefficients, and the area under the receiver operating characteristic curve (AUC).

Results. The DL-CAD system achieved an average accuracy of 78%, sensitivity of 60%, and specificity of 84% for detecting lesions in the prostate. The Dice similarity coefficient for prostate segmentation was 0.71, and the AUC was 81.16%. The system demonstrated high specificity in reducing false-positive results, which, after further optimization, could help minimize unnecessary biopsies and overtreatment.

Conclusion. The DL-CAD system shows potential in supporting clinical decision-making for patients with clinically significant PCa by improving diagnostic accuracy, particularly in minimizing intra- and inter-observer variability. Despite its high specificity, improvements in sensitivity and segmentation accuracy are needed, which could be achieved by using larger datasets and advanced deep learning techniques. Further multicenter validation is required for accelerated integration of this system into clinical practice.

Full Text

Restricted Access

About the authors

He Mingze

Institute of Urology and Reproductive Health, FGBOU VO Pavlov First Saint Petersburg State Medical University of the Ministry of Health of Russia

Author for correspondence.
Email: hemingze97@gmail.com
ORCID iD: 0000-0003-0601-4713

Postgraduate student of the Institute

Russian Federation, Moscow

M. E. Enikeev

Institute of Urology and Reproductive Health, FGBOU VO Pavlov First Saint Petersburg State Medical University of the Ministry of Health of Russia

Email: enikmic@mail.ru
ORCID iD: 0000-0002-3007-1315

Dr.Med.Sci., professor of the Institute

Russian Federation, Moscow

R. T. Rzayev

Institute of Urology and Reproductive Health, FGBOU VO Pavlov First Saint Petersburg State Medical University of the Ministry of Health of Russia

Email: ramin-rz@mail.ru
ORCID iD: 0000-0002-6005-6247

Cand.Med.Sci., Department of Radiology, the Second University Hospital

Russian Federation, Moscow

I. Chernenkiy

Institute of Urology and Reproductive Health, FGBOU VO Pavlov First Saint Petersburg State Medical University of the Ministry of Health of Russia

Email: chernenkiy_i_m@staff.sechenov.ru
ORCID iD: 0000-0001-5968-9883

Senior IT engineer, Center for Neural Network Technologies

Russian Federation, Moscow

M. V. Feldsherov

FGBOU VO Pavlov First Saint Petersburg State Medical University of the Ministry of Health of Russia

Email: feldsherov_m_v@staff.sechenov.ru

Head of the Department of Radiology, The Second University Hospital

Russian Federation, Moscow

Li He

The First Hospital of Jilin University

Email: lihe2018@jlu.edu.cn

Cand.Med.Sci., Department of Radiology

China, Changchun

Hu Kebang

The First Hospital of Jilin University

Email: hukb@jlu.edu.cn
ORCID iD: 0000-0003-2860-276X

Dr. Med. Sci., professor of the Department of Urology

China, Changchun

E. V. Shpot

Institute of Urology and Reproductive Health, FGBOU VO Pavlov First Saint Petersburg State Medical University of the Ministry of Health of Russia

Email: shpot_e_v@staff.sechenov.ru
ORCID iD: 0000-0003-1121-9430

Dr.Med.Sci., professor of the Institute

Russian Federation, Moscow

P. V. Glybochko

Institute of Urology and Reproductive Health, FGBOU VO Pavlov First Saint Petersburg State Medical University of the Ministry of Health of Russia

Email: rector@staff.sechenov.ru
ORCID iD: 0000-0002-5541-2251

Dr.Med.Sci., professor, academician of the Russian Academy of Sciences

Russian Federation, Moscow

References

  1. Song JM, Kim CB, Chung HC, Kane RL. Prostate-specific antigen, digital rectal examination and transrectal ultrasonography: a meta-analysis for this diagnostic triad of prostate cancer in symptomatic korean men. Yonsei medical journal. 2005;46(3):414-24. doi: 10.3349/ymj.2005.46.3.414.
  2. Moe A, Hayne D. Transrectal ultrasound biopsy of the prostate: does it still have a role in prostate cancer diagnosis? Translational andrology and urology. 2020;9(6):3018-24. doi: 10.21037/tau.2019.09.37.
  3. Rezvykh I.A., Rapoport L.M., Belysheva E.S. et al. mpMRI in planning nerve-sparing RARP in patients with localized prostate cancer of low and intermediate risk of progression. Pilot research. Russian Electronic Journal of Radiology. 2020;10(2):140-147. doi: 10.21569/2222-7415-2020-10-2-140-147. Russian (Резвых И.А., Рапопорт Л.М., Белышева Е.С. и др. МПМРТ в планировании нервосберегающей робот-ассистированной радикальной простатэктомии у больных с локализованным раком предстательной железы низкого и промежуточного рисков прогрессии. Пилотное исследование/ Российский электронный журнал лучевой диагностики. 2020;10(2):140-147. doi: 10.21569/2222-7415-2020-10-2-140-147).
  4. Rezvykh I.A., Rapoport L.M., Chuvalov L.L. Multiparametric MRI in planning of organ-sparing robot-assisted radical prostatectomy for treatment of localized prostate cancer with low and intermediate risk of progression. Andrology and Genital Surgery. 2021; 22 (2): 35-44. doi: 10.17650/1726-9784-2021-22-2-35-44. Russian (Резвых И.А., Рапопорт Л.М., Чувалов Л.Л. и др. Мультипараметрическая МРТ в планировании анатомосберегающей робот-ассистированной радикальной простатэктомии при локализованном раке предстательной железы низкого и промежуточного риска прогрессирования. Андрология и генитальная хирургия. 2021; 22 (2): 35-44. doi: 10.17650/1726-9784-2021-22-2-35-44).
  5. Benelli A, Vaccaro C, Guzzo S, Nedbal C, Varca V, Gregori A. The role of MRI/TRUS fusion biopsy in the diagnosis of clinically significant prostate cancer. Therapeutic advances in urology. 2020;12:1756287220916613. doi: 10.1177/1756287220916613.
  6. Kasivisvanathan V, Rannikko AS, Borghi M, Panebianco V, Mynderse LA, Vaarala MH, et al. MRI-Targeted or Standard Biopsy for Prostate-Cancer Diagnosis. The New England journal of medicine. 2018;378(19):1767-77. doi: 10.1056/NEJMoa1801993.
  7. Weinreb JC, Barentsz JO, Choyke PL, Cornud F, Haider MA, Macura KJ, et al. PI-RADS Prostate Imaging - Reporting and Data System: 2015, Version 2. European urology. 2016;69(1):16-40. doi: 10.1016/j.eururo.2015.08.052.
  8. van der Leest M, Cornel E, Israël B, Hendriks R, Padhani AR, Hoogenboom M, et al. Head-to-head Comparison of Transrectal Ultrasound-guided Prostate Biopsy Versus Multiparametric Prostate Resonance Imaging with Subsequent Magnetic Resonance-guided Biopsy in Biopsy-naïve Men with Elevated Prostate-specific Antigen: A Large Prospective Multicenter Clinical Study. European urology. 2019;75(4):570-8. doi: 10.1016/j.eururo.2018.11.023.
  9. Gupta RT, Mehta KA, Turkbey B, Verma S. PI-RADS: Past, present, and future. Journal of magnetic resonance imaging : JMRI. 2020;52(1):33-53. doi: 10.1002/jmri.26896.
  10. Song Y, Zhang YD, Yan X, Liu H, Zhou M, Hu B, et al. Computer-aided diagnosis of prostate cancer using a deep convolutional neural network from multiparametric MRI. Journal of magnetic resonance imaging : JMRI. 2018;48(6):1570-7. doi: 10.1002/jmri.26047.
  11. Sanders JW, Mok H, Hanania AN, Venkatesan AM, Tang C, Bruno TL, et al. Computer-aided segmentation on MRI for prostate radiotherapy, Part I: Quantifying human interobserver variability of the prostate and organs at risk and its impact on radiation dosimetry. Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology. 2022;169:124-31. doi: 10.1016/j.radonc.2021.12.011.
  12. Brembilla G, Dell’Oglio P, Stabile A, Damascelli A, Brunetti L, Ravelli S, et al. Interreader variability in prostate MRI reporting using Prostate Imaging Reporting and Data System version 2.1. European radiology. 2020;30(6):3383-92. doi: 10.1007/s00330-019-06654-2.
  13. Smith CP, Harmon SA, Barrett T, Bittencourt LK, Law YM, Shebel H, et al. Intra- and interreader reproducibility of PI-RADSv2: A multireader study. Journal of magnetic resonance imaging : JMRI. 2019;49(6):1694-703. doi: 10.1002/jmri.26555.
  14. Barragán-Montero A, Javaid U, Valdés G, Nguyen D, Desbordes P, Macq B, et al. Artificial intelligence and machine learning for medical imaging: A technology review. Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB). 2021;83:242-56. doi: 10.1016/j.ejmp.2021.04.016.
  15. Yang R, Yu Y. Artificial Convolutional Neural Network in Object Detection and Semantic Segmentation for Medical Imaging Analysis. Frontiers in oncology. 2021;11:638182. doi: 10.3389/fonc.2021.638182.
  16. He M, Cao Y, Chi C, Yang X, Ramin R, Wang S, et al. Research progress on deep learning in magnetic resonance imaging-based diagnosis and treatment of prostate cancer: a review on the current status and perspectives. Front Oncol. 2023;13:1189370. doi: 10.3389/fonc.2023.1189370.
  17. Chen F, Cen S, Palmer S. Application of Prostate Imaging Reporting and Data System Version 2 (PI-RADS v2): Interobserver Agreement and Positive Predictive Value for Localization of Intermediate- and High-Grade Prostate Cancers on Multiparametric Magnetic Resonance Imaging. Academic radiology. 2017;24(9):1101-6. doi: 10.1016/j.acra.2017.03.019.
  18. Girometti R, Giannarini G, Greco F, Isola M, Cereser L, Como G, et al. Interreader agreement of PI-RADS v. 2 in assessing prostate cancer with multiparametric MRI: A study using whole-mount histology as the standard of reference. Journal of magnetic resonance imaging : JMRI. 2019;49(2):546-55. doi: 10.1002/jmri.26220.
  19. Min X, Li M, Dong D, Feng Z, Zhang P, Ke Z, et al. Multi-parametric MRI-based radiomics signature for discriminating between clinically significant and insignificant prostate cancer: Cross-validation of a machine learning method. Eur J Radiol. 2019;115:16-21. doi: 10.1016/j.ejrad.2019.03.010.
  20. Liu Y, Zheng H, Liang Z, Miao Q, Brisbane WG, Marks LS, et al. Textured-Based Deep Learning in Prostate Cancer Classification with 3T Multiparametric MRI: Comparison with PI-RADS-Based Classification. Diagnostics (Basel, Switzerland). 2021;11(10). doi: 10.3390/diagnostics11101785.
  21. Aldoj N, Lukas S, Dewey M, Penzkofer T. Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network. Eur Radiol. 2020;30(2):1243-53. doi: 10.1007/s00330-019-06417-z.
  22. Saha A, Bosma JS, Twilt JJ, van Ginneken B, Bjartell A, Padhani AR, et al. Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study. Lancet Oncol. 2024;25(7):879-87. doi: 10.1016/s1470-2045(24)00220-1.
  23. Hoar D, Lee PQ, Guida A, Patterson S, Bowen CV, Merrimen J, et al. Combined Transfer Learning and Test-Time Augmentation Improves Convolutional Neural Network-Based Semantic Segmentation of Prostate Cancer from Multi-Parametric MR Images. Comput Methods Programs Biomed. 2021;210:106375. doi: 10.1016/j.cmpb.2021.106375.
  24. Cao R, Mohammadian Bajgiran A, Afshari Mirak S, Shakeri S, Zhong X, Enzmann D, et al. Joint Prostate Cancer Detection and Gleason Score Prediction in mp-MRI via FocalNet. IEEE Trans Med Imaging. 2019;38(11):2496-506. doi: 10.1109/tmi.2019.2901928.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Patient selection diagram

Download (190KB)
Indexing metadata
3. Fig. 2. MRI images. Segmentation and labeling of the prostate gland and tumor. A — Manual segmentation of the prostate gland; B — Manual segmentation of the lesion.

Download (262KB)
Indexing metadata
4. Fig. 3. 3D U-Net neural network diagram

Download (166KB)
Indexing metadata
5. Fig. 4. Diagnostic indicators of the developed DL-CAD system

Download (230KB)
Indexing metadata

Copyright (c) 2024 Bionika Media