Skip to main content

Advertisement

SpringerLink
Log in

Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods

  • Pelvis
  • Published:
Abdominal Radiology Aims and scope Submit manuscript

Abstract

Objective

Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters.

Materials and methods

A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model.

Results

683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05–329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707–0.971), 0.873 (0–0.997), and 0.894 (0.025–0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001).

Conclusion

Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data Availability

N/A.

Code Availability

N/A.

References

  1. Mattiuzzi C, Lippi G. Current Cancer Epidemiology. J Epidemiol Glob Health. 2019;9(4):217-222. https://doi.org/10.2991/jegh.k.191008.001

    Article  PubMed  PubMed Central  Google Scholar 

  2. Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA Cancer J Clin. 2023;73(1):17-48. https://doi.org/10.3322/caac.21763

    Article  PubMed  Google Scholar 

  3. Schatten H. Brief Overview of Prostate Cancer Statistics, Grading, Diagnosis and Treatment Strategies. In: Schatten H, ed. Cell & Molecular Biology of Prostate Cancer: Updates, Insights and New Frontiers. Advances in Experimental Medicine and Biology. Springer International Publishing; 2018:1–14. https://doi.org/10.1007/978-3-319-95693-0_1

  4. Kasivisvanathan V, Rannikko AS, Borghi M, et al. MRI-targeted or standard biopsy for prostate-cancer diagnosis. N Engl J Med. 2018;378(19):1767-1777.

    Article  PubMed  PubMed Central  Google Scholar 

  5. Ahdoot M, Wilbur AR, Reese SE, et al. MRI-Targeted, Systematic, and Combined Biopsy for Prostate Cancer Diagnosis. N Engl J Med. 2020;382(10):917-928. https://doi.org/10.1056/NEJMoa1910038

    Article  PubMed  PubMed Central  Google Scholar 

  6. Rouvière O, Puech P, Renard-Penna R, et al. Use of prostate systematic and targeted biopsy on the basis of multiparametric MRI in biopsy-naive patients (MRI-FIRST): a prospective, multicentre, paired diagnostic study. Lancet Oncol. 2019;20(1):100-109.

    Article  PubMed  Google Scholar 

  7. Bass EJ, Pantovic A, Connor MJ, et al. Diagnostic accuracy of magnetic resonance imaging targeted biopsy techniques compared to transrectal ultrasound guided biopsy of the prostate: a systematic review and meta-analysis. Prostate Cancer Prostatic Dis. 2022;25(2):174-179.

    Article  CAS  PubMed  Google Scholar 

  8. Bezinque A, Moriarity A, Farrell C, Peabody H, Noyes SL, Lane BR. Determination of Prostate Volume: A Comparison of Contemporary Methods. Acad Radiol. 2018;25(12):1582-1587. https://doi.org/10.1016/j.acra.2018.03.014

    Article  PubMed  Google Scholar 

  9. Wu M, He X, Li F, Zhu J, Wang S, Burstein PD. Weakly supervised volumetric prostate registration for MRI-TRUS image driven by signed distance map. Comput Biol Med. 2023;163:107150. https://doi.org/10.1016/j.compbiomed.2023.107150

    Article  PubMed  Google Scholar 

  10. Eskicorapci SY, Guliyev F, Akdogan B, Dogan HS, Ergen A, Ozen H. INDIVIDUALIZATION OF THE BIOPSY PROTOCOL ACCORDING TO THE PROSTATE GLAND VOLUME FOR PROSTATE CANCER DETECTION. J Urol. 2005;173(5):1536-1540. https://doi.org/10.1097/01.ju.0000154242.60413.3d

    Article  PubMed  Google Scholar 

  11. Cornud F, Roumiguié M, Barry de Longchamps N, et al. Precision Matters in MR Imaging-targeted Prostate Biopsies: Evidence from a Prospective Study of Cognitive and Elastic Fusion Registration Transrectal Biopsies. Radiology. 2018;287(2):534–542. https://doi.org/10.1148/radiol.2017162916

  12. Age-related changes of the prostate: evaluation by MR imaging. https://doi.org/10.2214/ajr.152.1.77

  13. Chan TW, Kressel HY. Prostate and seminal vesicles after irradiation: MR appearance. J Magn Reson Imaging. 1991;1(5):503-511. https://doi.org/10.1002/jmri.1880010502

    Article  CAS  PubMed  Google Scholar 

  14. Patel P, Mathew MS, Trilisky I, Oto A. Multiparametric MR Imaging of the Prostate after Treatment of Prostate Cancer. RadioGraphics. 2018;38(2):437-449. https://doi.org/10.1148/rg.2018170147

    Article  PubMed  Google Scholar 

  15. Cannarella R, Condorelli RA, Barbagallo F, La Vignera S, Calogero AE. Endocrinology of the Aging Prostate: Current Concepts. Front Endocrinol. 2021;12:554078. https://doi.org/10.3389/fendo.2021.554078

    Article  Google Scholar 

  16. Montagne S, Hamzaoui D, Allera A, et al. Challenge of prostate MRI segmentation on T2-weighted images: inter-observer variability and impact of prostate morphology. Insights Imaging. 2021;12(1):71. https://doi.org/10.1186/s13244-021-01010-9

    Article  PubMed  PubMed Central  Google Scholar 

  17. Becker AS, Chaitanya K, Schawkat K, et al. Variability of manual segmentation of the prostate in axial T2-weighted MRI: A multi-reader study. Eur J Radiol. 2019;121:108716. https://doi.org/10.1016/j.ejrad.2019.108716

    Article  PubMed  Google Scholar 

  18. Turkbey B, Fotin SV, Huang RJ, et al. Fully Automated Prostate Segmentation on MRI: Comparison With Manual Segmentation Methods and Specimen Volumes. Am J Roentgenol. 2013;201(5):W720-W729. https://doi.org/10.2214/AJR.12.9712

    Article  Google Scholar 

  19. Ushinsky A, Bardis M, Glavis-Bloom J, et al. A 3D-2D Hybrid U-Net Convolutional Neural Network Approach to Prostate Organ Segmentation of Multiparametric MRI. Am J Roentgenol. 2021;216(1):111-116. https://doi.org/10.2214/AJR.19.22168

    Article  Google Scholar 

  20. Clark T, Wong A, Haider MA, Khalvati F. Fully Deep Convolutional Neural Networks for Segmentation of the Prostate Gland in Diffusion-Weighted MR Images. In: Karray F, Campilho A, Cheriet F, eds. Image Analysis and Recognition. Lecture Notes in Computer Science. Springer International Publishing; 2017:97–104. https://doi.org/10.1007/978-3-319-59876-5_12

  21. Litjens G, Toth R, van de Ven W, et al. Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. Med Image Anal. 2014;18(2):359-373. https://doi.org/10.1016/j.media.2013.12.002

    Article  PubMed  Google Scholar 

  22. Ghose S, Oliver A, Martí R, et al. A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images. Comput Methods Programs Biomed. 2012;108(1):262-287. https://doi.org/10.1016/j.cmpb.2012.04.006

    Article  PubMed  Google Scholar 

  23. Mutasa S, Sun S, Ha R. Understanding artificial intelligence based radiology studies: What is overfitting? Clin Imaging. 2020;65:96-99. https://doi.org/10.1016/j.clinimag.2020.04.025

    Article  PubMed  PubMed Central  Google Scholar 

  24. Eche T, Schwartz LH, Mokrane FZ, Dercle L. Toward Generalizability in the Deployment of Artificial Intelligence in Radiology: Role of Computation Stress Testing to Overcome Underspecification. Radiol Artif Intell. 2021;3(6):e210097. https://doi.org/10.1148/ryai.2021210097

    Article  PubMed  PubMed Central  Google Scholar 

  25. Sanford TH, Zhang L, Harmon SA, et al. Data Augmentation and Transfer Learning to Improve Generalizability of an Automated Prostate Segmentation Model. AJR Am J Roentgenol. 2020;215(6):1403-1410. https://doi.org/10.2214/AJR.19.22347

    Article  PubMed  PubMed Central  Google Scholar 

  26. Liu S, Xu D, Zhou SK, et al. 3d anisotropic hybrid network: Transferring convolutional features from 2d images to 3d anisotropic volumes. In: Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16–20, 2018, Proceedings, Part II 11. Springer; 2018:851–858.

  27. Zhang L, Wang X, Yang D, et al. When unseen domain generalization is unnecessary? rethinking data augmentation. ArXiv Prepr ArXiv190603347. Published online 2019.

  28. Sarma KV, Harmon S, Sanford T, et al. Federated learning improves site performance in multicenter deep learning without data sharing. J Am Med Inform Assoc JAMIA. 2021;28(6):1259-1264. https://doi.org/10.1093/jamia/ocaa341

    Article  PubMed  Google Scholar 

  29. Liu Y, Miao Q, Surawech C, et al. Deep Learning Enables Prostate MRI Segmentation: A Large Cohort Evaluation With Inter-Rater Variability Analysis. Front Oncol. 2021;11. Accessed July 7, 2023. https://www.frontiersin.org/articles/10.3389/fonc.2021.801876

  30. Korsager AS, Fortunati V, van der Lijn F, et al. The use of atlas registration and graph cuts for prostate segmentation in magnetic resonance images. Med Phys. 2015;42(4):1614-1624. https://doi.org/10.1118/1.4914379

    Article  PubMed  Google Scholar 

  31. Bhavsar A, Verma S. Anatomic Imaging of the Prostate. BioMed Res Int. 2014;2014:e728539. https://doi.org/10.1155/2014/728539

    Article  Google Scholar 

  32. Zeng Q, Samei G, Karimi D, et al. Prostate segmentation in transrectal ultrasound using magnetic resonance imaging priors. Int J Comput Assist Radiol Surg. 2018;13(6):749-757. https://doi.org/10.1007/s11548-018-1742-6

    Article  PubMed  Google Scholar 

Download references

Funding

This research is funded by intramural research program of NIH.

Author information

Authors and Affiliations

  1. Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA

    Latrice A. Johnson, Stephanie A. Harmon, Enis C. Yilmaz, Yue Lin, Mason J. Belue, Katie M. Merriman, Nathan S. Lay, Peter L. Choyke & Baris Turkbey

  2. Department of Urology, Hawaii Pacific Health, Honolulu, HI, USA

    Thomas H. Sanford

  3. Department of Psychiatry and Behavioral Sciences, University of California, San Francisco, CA, USA

    Karthik V. Sarma

  4. Department of Radiology, University of California, Los Angeles, Los Angeles, CA, USA

    Corey W. Arnold

  5. NVIDIA Corporation, Santa Clara, CA, USA

    Ziyue Xu, Holger R. Roth, Dong Yang, Jesse Tetreault & Daguang Xu

  6. Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA

    Krishnan R. Patel & Deborah E. Citrin

  7. Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA

    Sandeep Gurram & Peter A. Pinto

  8. Center for Interventional Oncology, National Cancer Institute, NIH, Bethesda, MD, USA

    Bradford J. Wood

  9. Department of Radiology, Clinical Center, NIH, Bethesda, MD, USA

    Bradford J. Wood

  10. Molecular Imaging Branch (B.T.), National Cancer Institute, National Institutes of Health, 10 Center Dr., MSC 1182, Building 10, Room B3B85, Bethesda, MD, 20892, USA

    Baris Turkbey

Authors
  1. Latrice A. Johnson
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stephanie A. Harmon
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Enis C. Yilmaz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yue Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mason J. Belue
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Katie M. Merriman
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Nathan S. Lay
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Thomas H. Sanford
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Karthik V. Sarma
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Corey W. Arnold
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Ziyue Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Holger R. Roth
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Dong Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Jesse Tetreault
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Daguang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Krishnan R. Patel
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Sandeep Gurram
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Bradford J. Wood
    View author publications

    You can also search for this author in PubMed Google Scholar

  19. Deborah E. Citrin
    View author publications

    You can also search for this author in PubMed Google Scholar

  20. Peter A. Pinto
    View author publications

    You can also search for this author in PubMed Google Scholar

  21. Peter L. Choyke
    View author publications

    You can also search for this author in PubMed Google Scholar

  22. Baris Turkbey
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Baris Turkbey.

Ethics declarations

Conflict of interest

Bradford J. Wood: Principal investigator on cooperative research and development agreement (CRADA) between National Institutes of Health (NIH) and Philips and CRADAs with industry partners unrelated to this work; travel support related to CRADAs; royalties from NIH related to Philips licensing agreement; patents planned, issued, or pending. Peter L. Choyke: Receives payment from royalties paid to the U.S. government for patents on MRI US fusion biopsy licensed to Philips Medical. Peter A. Pinto: Institutional CRADA with Philips; royalties from NIH related to Philips licensing agreement; NIH-related patents planned, issued, or pending (U.S. patent nos. 8 447 384 and 10 215 830). Baris Turkbey: CRADAs with NVIDIA and Philips; royalties from NIH; patents planned, issued, or pending in the field of artificial intelligence. Dong Yang, Ziyue Xu, Holger Roth, Jesse Tetreault, Daguang Xu: employee of NVIDIA Corporation.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Consent to participate

Informed consent was obtained from all individual participants included in the study.

Consent for publication

All coauthors are aware of submission of this work, and they approved the submission.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 33 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Johnson, L.A., Harmon, S.A., Yilmaz, E.C. et al. Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods. Abdom Radiol (2024). https://doi.org/10.1007/s00261-024-04242-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00261-024-04242-7

Keywords

Search

Navigation