"skipMainNavigation"
Search
Quick Search in Journals
Quick Search anywhere
Advanced Search
Radiology
Menu
Previous
Next
Original Research

Fully Automated Deep Learning Model to Detect Clinically Significant Prostate Cancer at MRI

  • Deputy Editor: Vicky Goh
  • Scientific Editor: Shannyn Wolfe
Published Online:Aug 6 2024https://doi.org/10.1148/radiol.232635
See also the editorial by Johnson and Chandarana in this issue.

Abstract

The performance of a deep learning model was not different from that of radiologists in the detection of clinically significant prostate cancer at MRI, and gradient-weighted class activation maps localized the tumor.

Background

Multiparametric MRI can help identify clinically significant prostate cancer (csPCa) (Gleason score ≥7) but is limited by reader experience and interobserver variability. In contrast, deep learning (DL) produces deterministic outputs.

Purpose

To develop a DL model to predict the presence of csPCa by using patient-level labels without information about tumor location and to compare its performance with that of radiologists.

Materials and Methods

Data from patients without known csPCa who underwent MRI from January 2017 to December 2019 at one of multiple sites of a single academic institution were retrospectively reviewed. A convolutional neural network was trained to predict csPCa from T2-weighted images, diffusion-weighted images, apparent diffusion coefficient maps, and T1-weighted contrast-enhanced images. The reference standard was pathologic diagnosis. Radiologist performance was evaluated as follows: Radiology reports were used for the internal test set, and four radiologists’ PI-RADS ratings were used for the external (ProstateX) test set. The performance was compared using areas under the receiver operating characteristic curves (AUCs) and the DeLong test. Gradient-weighted class activation maps (Grad-CAMs) were used to show tumor localization.

Results

Among 5735 examinations in 5215 patients (mean age, 66 years ± 8 [SD]; all male), 1514 examinations (1454 patients) showed csPCa. In the internal test set (400 examinations), the AUC was 0.89 and 0.89 for the DL classifier and radiologists, respectively (P = .88). In the external test set (204 examinations), the AUC was 0.86 and 0.84 for the DL classifier and radiologists, respectively (P = .68). DL classifier plus radiologists had an AUC of 0.89 (P < .001). Grad-CAMs demonstrated activation over the csPCa lesion in 35 of 38 and 56 of 58 true-positive examinations in internal and external test sets, respectively.

Conclusion

The performance of a DL model was not different from that of radiologists in the detection of csPCa at MRI, and Grad-CAMs localized the tumor.

© RSNA, 2024

Supplemental material is available for this article.

See also the editorial by Johnson and Chandarana in this issue.

Download as PowerPoint

References

  • 1. Ferlay J, Colombet M, Soerjomataram I, et al. Estimating the global cancer incidence and mortality in 2018: GLOBOCAN sources and methods. Int J Cancer 2019;144(8):1941–1953.
    MedlineGoogle Scholar
  • 2. Stabile A, Giganti F, Rosenkrantz AB, et al. Multiparametric MRI for prostate cancer diagnosis: current status and future directions. Nat Rev Urol 2020;17(1):41–61.
    MedlineGoogle Scholar
  • 3. Turkbey B, Rosenkrantz AB, Haider MA, et al. Prostate Imaging Reporting and Data System version 2.1: 2019 update of Prostate Imaging Reporting and Data System version 2. Eur Urol 2019;76(3):340–351.
    MedlineGoogle Scholar
  • 4. Smith CP, Harmon SA, Barrett T, et al. Intra- and interreader reproducibility of PI-RADSv2: a multireader study. J Magn Reson Imaging 2019;49(6):1694–1703.
    MedlineGoogle Scholar
  • 5. Bonekamp D, Kohl S, Wiesenfarth M, et al. Radiomic machine learning for characterization of prostate lesions with MRI: comparison to ADC values. Radiology 2018;289(1):128–137.
    Google Scholar
  • 6. Lay N, Tsehay Y, Greer MD, et al. Detection of prostate cancer in multiparametric MRI using random forest with instance weighting. J Med Imaging (Bellingham) 2017;4(2):024506.
    MedlineGoogle Scholar
  • 7. Hiremath A, Shiradkar R, Fu P, et al. An integrated nomogram combining deep learning, Prostate Imaging-Reporting and Data System (PI-RADS) scoring, and clinical variables for identification of clinically significant prostate cancer on biparametric MRI: a retrospective multicentre study. Lancet Digit Health 2021;3(7):e445–e454.
    MedlineGoogle Scholar
  • 8. Hamm CA, Baumgärtner GL, Biessmann F, et al. Interactive explainable deep learning model informs prostate cancer diagnosis at MRI. Radiology 2023;307(4):e222276.
    Google Scholar
  • 9. Saha A, Hosseinzadeh M, Huisman H. End-to-end prostate cancer detection in bpMRI via 3D CNNs: effects of attention mechanisms, clinical priori and decoupled false positive reduction. Med Image Anal 2021;73:102155.
    MedlineGoogle Scholar
  • 10. Hosseinzadeh M, Saha A, Brand P, Slootweg I, de Rooij M, Huisman H. Deep learning-assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge. Eur Radiol 2022;32(4):2224–2234.
    MedlineGoogle Scholar
  • 11. Arif M, Schoots IG, Castillo Tovar J, et al. Clinically significant prostate cancer detection and segmentation in low-risk patients using a convolutional neural network on multi-parametric MRI. Eur Radiol 2020;30(12):6582–6592.
    MedlineGoogle Scholar
  • 12. Pellicer-Valero OJ, Marenco Jiménez JL, Gonzalez-Perez V, et al. Deep learning for fully automatic detection, segmentation, and Gleason grade estimation of prostate cancer in multiparametric magnetic resonance images. Sci Rep 2022;12(1):2975.
    MedlineGoogle Scholar
  • 13. 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):411–417.
    MedlineGoogle Scholar
  • 14. Schelb P, Kohl S, Radtke JP, et al. Classification of cancer at prostate MRI: deep learning versus clinical PI-RADS assessment. Radiology 2019;293(3):607–617.
    Google Scholar
  • 15. Rajagopal A, Redekop E, Kemisetti A, et al. Federated learning with research prototypes: application to multi-center MRI-based detection of prostate cancer with diverse histopathology. Acad Radiol 2023;30(4):644–657.
    MedlineGoogle Scholar
  • 16. Cao R, Mohammadian Bajgiran A, Afshari Mirak S, et al. Joint prostate cancer detection and Gleason score prediction in mp-MRI via FocalNet. IEEE Trans Med Imaging 2019;38(11):2496–2506.
    MedlineGoogle Scholar
  • 17. Bhattacharya I, Seetharaman A, Kunder C, et al. Selective identification and localization of indolent and aggressive prostate cancers via CorrSigNIA: an MRI-pathology correlation and deep learning framework. Med Image Anal 2022;75:102288.
    MedlineGoogle Scholar
  • 18. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis 2016;128(2):336–359.
    Google Scholar
  • 19. Nordström T, Discacciati A, Bergman M, et al; STHLM3 study group. Prostate cancer screening using a combination of risk-prediction, MRI, and targeted prostate biopsies (STHLM3-MRI): a prospective, population-based, randomised, open-label, non-inferiority trial. Lancet Oncol 2021;22(9):1240–1249.
    MedlineGoogle Scholar
  • 20. Eldred-Evans D, Burak P, Connor MJ, et al. Population-based prostate cancer screening with magnetic resonance imaging or ultrasonography: the IP1-PROSTAGRAM Study. JAMA Oncol 2021;7(3):395–402.
    MedlineGoogle Scholar
  • 21. Litjens G, Debats O, Barentsz J, Karssemeijer N, Huisman H. SPIE-AAPM PROSTATEx Challenge Data (Version 2). The Cancer Imaging Archive. https://www.cancerimagingarchive.net/collection/prostatex/. Updated July 5, 2022. Accessed July 5, 2024.
    Google Scholar
  • 22. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention 2015. Lecture Notes in Computer Science, volume 9351; Springer, Cham: 234–241.
    Google Scholar
  • 23. Huang SC, Pareek A, Seyyedi S, Banerjee I, Lungren MP. Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines. NPJ Digit Med 2020;3(1):136.
    MedlineGoogle Scholar
  • 24. Woo S, Suh CH, Kim SY, Cho JY, Kim SH. Diagnostic performance of Prostate Imaging Reporting and Data System version 2 for detection of prostate cancer: a systematic review and diagnostic meta-analysis. Eur Urol 2017;72(2):177–188.
    MedlineGoogle Scholar
  • 25. Bosma JS, Saha A, Hosseinzadeh M, Slootweg I, de Rooij M, Huisman H. Semisupervised learning with report-guided pseudo labels for deep learning-based prostate cancer detection using biparametric MRI. Radiol Artif Intell 2023;5(5):e230031.
    Google Scholar
  • 26. Althnian A, AlSaeed D, Al-Baity H, Samha A, Dris A. Impact of dataset size on classification performance: an empirical evaluation in the medical domain. Appl Sci (Basel) 2021;11(2):796.
    Google Scholar
  • 27. Ghorbani A, Abid A, Zou J. Interpretation of neural networks is fragile. Proc AAAI Conf Artif Intell 2019,33(01):3681–3688.
    Google Scholar
  • 28. Kindermans PJ, Hooker S, Adebayo J, et al. The (Un)reliability of saliency methods. In: Samek W, Montavon G, Vedaldi A, Hansen L, Müller KR, eds. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Lecture Notes in Computer Science, volume 11700. Springer, Cham: 267–280.
    Google Scholar

Article History

Received: Oct 4 2023
Revision requested: Dec 13 2023
Revision received: Apr 10 2024
Accepted: Apr 25 2024
Published online: Aug 06 2024