Application of artificial intelligence in patients with MRI-invisible prostate cancer

Cover Page

Cite item

Full Text

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

Abstract

Background. Given the prevalence of prostate cancer (PCa) worldwide, the growing role of magnetic resonance imaging (MRI) in the diagnosis of PCa, and the fact that a fairly high percentage of clinically significant tumors remain undiagnosed, there is a need for a tool capable of increasing the diagnostic accuracy of MRI.

Aim. We attempted to create an artificial intelligence (AI) model and evaluate it in the diagnosis of malignant tumors based on MRI in patients with so-called MRI-invisible PCa.

Materials and methods. The study was conducted at the Clinical and Diagnostics Center “Health” in Rostov-on-Don. A total of 151 patients with localized PCa were included, who underwent robot-assisted radical prostatectomy between 2022 and 2023. The patients selected for the study underwent MRI on a Phillips Ingenia 3.0T machine according to the multiparametric MRI protocol of the prostate gland by two experienced radiologists, in accordance with the requirements of PI-RADS v.2.1. A standard histological examination was performed by a morphologist according to the diagnostic protocol. The obtained data were used to train a convolutional neural network based on the U-Net architecture.

Results. Using AI, the diagnosis of PCa was correctly determined in 78.1 % of cases (n = 118), including 94 men with focal lesions on multiparametric MRI and 24 patients with no changes in the prostate gland. When assessing the correctness of the diagnosis depending on the nature of the lesion, it was found that with focal accumulation of PCa, it was verified in 74.6 % of cases (n = 94) and not verified in 25.4 % (n = 32); with no changes it was verified in 96.0 % (n = 24) of cases and not verified in 4.0 % (n = 1) cases (p = 0.016).

Conclusion. We have developed and evaluated an AI model based on supervised machine learning. This model allows not only to speed up the diagnosis, but also to increase the chances of a correct diagnosis in patients with MRI-invisible PCa 8.17-fold (95 % confidence interval 1.06–62.85).

About the authors

I. A. Aboyan

Clinical and Diagnostics Center “Health” in Rostov-on-Don

Email: polyakov.andrey.00@mail.ru
ORCID iD: 0000-0002-2798-368X
Russian Federation, 70/3 Dolomanovskiy Pereulok, Rostov-on-Don 344011

S. M. Pakus

Clinical and Diagnostics Center “Health” in Rostov-on-Don

Email: polyakov.andrey.00@mail.ru
ORCID iD: 0000-0001-6468-5983
Russian Federation, 70/3 Dolomanovskiy Pereulok, Rostov-on-Don 344011

Andrey S. Polyakov

Clinical and Diagnostics Center “Health” in Rostov-on-Don

Author for correspondence.
Email: polyakov.andrey.00@mail.ru
ORCID iD: 0009-0007-9589-5458
Russian Federation, 70/3 Dolomanovskiy Pereulok, Rostov-on-Don 344011

V. A. Redkin

Clinical and Diagnostics Center “Health” in Rostov-on-Don

Email: polyakov.andrey.00@mail.ru
Russian Federation, 70/3 Dolomanovskiy Pereulok, Rostov-on-Don 344011

K. I. Badyan

Clinical and Diagnostics Center “Health” in Rostov-on-Don

Email: polyakov.andrey.00@mail.ru
ORCID iD: 0009-0000-1944-8380
Russian Federation, 70/3 Dolomanovskiy Pereulok, Rostov-on-Don 344011

K. A. Shiranov

Clinical and Diagnostics Center “Health” in Rostov-on-Don

Email: polyakov.andrey.00@mail.ru
Russian Federation, 70/3 Dolomanovskiy Pereulok, Rostov-on-Don 344011

D. I. Pakus

Oncology Dispensary, Rostov-on-Don

Email: polyakov.andrey.00@mail.ru
Russian Federation, 9 Sokolova Prospekt, Rostov-on-Don 344011

References

  1. Bray F., Laversanne M., Sung H. et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2024;74(3):229–63. doi: 10.3322/caac.21834
  2. Cornford P., van den Bergh R.C.N., Briers E. et al. EAU-EANM-ESTRO-ESUR-ISUP-SIOG Guidelines on Prostate Cancer – 2024 Update. Part I: Screening, Diagnosis, and Local Treatment with Curative Intent. Eur Urol 2024;86(2):148–63. doi: 10.1016/j.eururo.2024.03.027
  3. Padhani A.R., Barentsz J., Villeirs G. et al. PI-RADS Steering Committee: The PI-RADS Multiparametric MRI and MRI-directed Biopsy Pathway. Radiology 2019;292(2):464–74. doi: 10.1148/radiol.2019182946
  4. Ahmed H.U., El-Shater Bosaily A., Brown L.C. et al. Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study. Lancet 2017;389(10071):815–22. doi: 10.1016/S0140-6736(16)32401-1
  5. Khoo A., Liu L.Y., Sadun T.Y. et al. Prostate cancer multiparametric magnetic resonance imaging visibility is a tumor-intrinsic phenomena. J Hematol Oncol 2022;15(1):48. doi: 10.1186/s13045-022-01268-6
  6. Pachynski R.K., Kim E.H., Miheecheva N. et al. Single-cell spatial proteomic revelations on the multiparametric MRI heterogeneity of clinically significant prostate cancer. Clin Cancer Res 2021;27(12):3478–90. doi: 10.1158/1078-0432.CCR-20-4217
  7. Fazekas T., Pallauf M., Kufel J. et al. Molecular correlates of prostate cancer visibility on multiparametric magnetic resonance imaging - a systematic review. Eur Urol Oncol 2025;8(5):1352–64. doi: 10.1016/j.euo.2024.09.017
  8. Fernandes M.C., Yildirim O., Woo S. et al. The role of MRI in prostate cancer: current and future directions. MAGMA 2022;35(4):503–21. doi: 10.1007/s10334-022-01006-6
  9. Muehlematter U.J., Daniore P., Vokinger K.N. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015–20): a comparative analysis. Lancet Digit Health 2021;3(3):e195–203. doi: 10.1016/S2589-7500(20)30292-2
  10. Scalco E., Rizzo G. Texture analysis of medical images for radiotherapy applications. Br J Radiol 2017;90(1070):20160642. doi: 10.1259/bjr.20160642
  11. Wibmer A., Hricak H., Gondo T. et al. Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. Eur Radiol 2015;25(10):2840–50. doi: 10.1007/s00330-015-3701-8
  12. Абоян И.А., Редькин В.А., Назарук М.Г. и др. Искусственный интеллект в диагностике рака предстательной железы с помощью магнитно-резонансной томографии. Новый подход. Онкоурология 2024;20(2):35–43. doi: 10.17650/1726-9776-2024-20-2-35-43 Aboyan I.A., Redkin V.A., Nazaruk M.G. et al. Artificial intelligence in diagnosis of prostate cancer using magnetic resonance imaging. New approach. Onkourologiya = Cancer Urology 2024;20(2):35–43. (In Russ.). doi: 10.17650/1726-9776-2024-20-2-35-43
  13. International Agency for Research on Cancer. Urinary and Male Genital Tumours. WHO Classification of Tumours. Ed.: H. Moch. International Agency for Research on Cancer, 2022;8:576.
  14. Brierley J., Gospodarowicz M.D., Wittekind C.T. TNM Classification of Malignant Tumors International Union Against Cancer. 8th edn. Oxford, England: Wiley, 2017. Pp. 57–62.
  15. Protocol for the Examination of Radical Prostatectomy Specimens From Patients With Carcinoma of the Prostate Gland. 2020.
  16. Ishioka J., Matsuoka Y., Uehara S. et al. Computer-aided diagnosis of prostate cancer on magnetic resonance imaging using a convolutional neural network algorithm. BJU Int 2018;122(3): 411–7. doi: 10.1111/bju.14397
  17. Tan N., Margolis D.J., Lu D.Y. et al. Characteristics of detected and missed prostate cancer foci on 3-T multiparametric MRI using an endorectal coil correlated with whole-mount thin-section histopathology. AJR Am J Roentgenol 2015;205(1):W87–92. doi: 10.2214/AJR.14.13285
  18. Cuocolo R., Brunella Cipullo M., Stanzione A. et al. Machine learning for the identification of clinically significant prostate cancer on MRI: a meta-analysis. Eur Radiol 2020;30(12):6877–87. doi: 10.1007/s00330-020-07027-w
  19. Zhong X., Cao R., Shakeri S. et al. Deep transfer learning-based prostate cancer classification using 3 Tesla multi-parametric MRI. Abdom Radiol 2019;44(6):2030–9. doi: 10.1007/s00261-018-1824-5
  20. Fehr D., Veeraraghavan H., Wibmer A. et al. Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proc Natl Acad Sci USA 2015;112(46):E6265–73. doi: 10.1073/pnas.1505935112
  21. Toivonen J., Montoya Perez I., Movahedi P. et al. Radiomics and machine learning of multisequence multiparametric prostate MRI: Towards improved non-invasive prostate cancer characterization. PLoS One 2019;14(7):e0217702. doi: 10.1371/journal.pone.0217702
  22. Aristidou A., Jena R., Topol E.J. Bridging the chasm between AI and clinical implementation. Lancet 2022;399(10325):620. doi: 10.1016/S0140-6736(22)00235-5
  23. Reyes M., Meier R., Pereira S. et al. On the interpretability of artificial intelligence in radiology: challenges and opportunities. Radiol Artif Intell 2020;2(3):e190043. doi: 10.1148/ryai.2020190043
  24. Cutillo C.M., Sharma K.R., Foschini L. et al. Machine intelligence in healthcare – perspectives on trustworthiness, explainability, usability, and transparency. NPJ Digital Med 2020:3:47. doi: 10.1038/s41746-020-0254-2
  25. Hamon R. Bridging the gap between AI and explainability in the GDPR: Towards trustworthiness-by-design in automated decision-making. IEEE 2022;17(1):72–85.
  26. Reddy S. Explainability and artificial intelligence in medicine. Lancet Digit Health 2022;4(4):e214–5. doi: 10.1016/S2589-7500(22)00029-2
  27. Hamm C.A., Baumgärtner G.L., Biessmann F. et al. Interactive explainable deep learning model informs prostate cancer diagnosis at MRI. Radiology 2023;307(4). doi: 10.1148/radiol.222276

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2026 ABV-Press

License URL: https://oncourology.abvpress.ru/oncur/about/editorialPolicies
СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № ФС 77-36986 от  21.07.2009.