Analysis of deep learning approaches for automated prostate segmentation: literature review

Background. Delineation of the prostate boundaries represents the initial step in understanding the state of the whole organ and is mainly manually performed, which takes a long time and directly depends on the experience of the radiologists. Automated prostate selection can be carried out by various approaches, including using artificial intelligence and its subdisciplines – machine and deep learning.
Aim. To reveal the most accurate deep learning-based methods for prostate segmentation on multiparametric magnetic resonance images.
Materials and methods. The search was conducted in July 2022 in the PubMed database with a special clinical query (((AI) OR (machine learning)) OR (deep learning)) AND (prostate) AND (MRI). The inclusion criteria were availability of the full article, publication date no more than five years prior to the time of the search, availability of a quantitative assessment of the reconstruction accuracy by the Dice similarity coefficient (DSC) calculation.
Results. The search returned 521 articles, but only 24 papers including descriptions of 33 different deep learning networks for prostate segmentation were selected for the final review. The median number of cases included for artificial intelligence training was 100 with a range from 25 to 365. The optimal DSC value threshold (0.9), in which automated segmentation is only slightly inferior to manual delineation, was achieved in 21 studies.
Conclusion. Despite significant achievements in the development of deep learning-based prostate segmentation algorithms, there are still problems and limitations that should be resolved before artificial intelligence can be implemented in clinical practice.

1. Kossov P.A., Chernyaev V.A., Akhverdieva G.I. et al. Role and significance of multiparametric magnetic resonance imaging in prostate cancer diagnostics. Onkourologiya = Cancer Urology 2017;13(1):122–33. (In Russ.). DOI: 10.17650/1726-9776-2017-13-1-122-133

2. Beetz N.L., Haas M., Baur A. et al. Inter-reader variability using PI-RADS v2 versus PI-RADS v2.1: most new disagreement stems from scores 1 and 2. Rofo 2022;194(8):852–61. DOI: 10.1055/a-1752-1038

3. Kovalev V.A., Voynov D.M., Malyshau V.D. et al. Computerized diagnosis of prostate cancer based on whole slide histology images and deep learning methods. Informatika = Informatics 2020;17(4): 48–60. (In Russ.). DOI: 10.37661/1816-0301-2020-17-4-48-60

4. Reva S.A., Shaderkin I.A., Zyatchin I.V. et al. Artificial intelligence in cancer urology. Eksperimental'naya i klinihceskaya urologiya = Experimental and Clinical Urology 2021;14(2):46–51. (In Russ.). DOI: 10.29188/2222-8543-2021-14-2-46-51

5. Da Silva G.L.F., Diniz P.S., Ferreira J.L. et al. Superpixel-based deep convolutional neural networks and active contour model for automatic prostate segmentation on 3D MRI scans. Med Biol Eng Comput 2020;58(9):1947–64. DOI: 10.1007/s11517-020-02199-5

6. Wang B., Lei Y., Tian S. et al. Deeply supervised 3D fully convolutional networks with group dilated convolution for automatic MRI prostate segmentation. Med Phys 2019;46(4):1707–18. DOI: 10.1002/mp.13416

7. Liu Q., Fu M., Gong X. et al. Densely dilated spatial pooling convolutional network using benign loss functions for imbalanced volumetric prostate segmentation. Curr Bioinform 2018;15(7):788–99. DOI: 10.48550/arXiv.1801.10517

8. Nai Y.H., Teo B.W., Tan N.L. et al. Evaluation of multimodal algorithms for the segmentation of multiparametric MRI prostate images. Comput Math Methods Med 2020;20;2020:8861035. DOI: 10.1155/2020/8861035

9. Yu L., Yang X., Chen H. et al. Volumetric ConvNets with mixed residual connections for automated prostate segmentation from 3D MR images. Proc AAAI Conf Artif Intell 2017;31(1):66–72. DOI: 10.1609/aaai.v31i1.10510

10. Comelli A., Dahiya N., Stefano A. et al. Deep learning-based methods for prostate segmentation in magnetic resonance imaging. Appl Sci 2021;11(2):1–13. DOI: 10.3390/app11020782

11. Karimi D., Samei G., Kesch C. et al. Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models. Int J Comput Assist Radiol Surg 2018;13(8):1211–9. DOI: 10.1007/s11548-018-1785-8

12. 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. AJR Am J Roentgenol 2021;216(1):111–6. DOI: 10.2214/AJR.19.22168

13. Yan K., Wang X., Kim J. et al. A propagation-DNN: deep combination learning of multi-level features for MR prostate segmentation. Comput Methods Programs Biomed 2019;170:11–21. DOI: 10.1016/j.cmpb.2018.12.031

14. Jia H., Xia Y., Song Y. et al. 3D APA-Net: 3D adversarial pyramid anisotropic convolutional network for prostate segmentation in MR images. IEEE Trans Med Imaging 2020;39(2):447–57. DOI: 10.1109/TMI.2019.2928056

15. Bardis M., Houshyar R., Chantaduly C. et al. Segmentation of the prostate transition zone and peripheral zone on MR images with deep learning. Radiol Imaging Cancer 2021;3(3):e200024. DOI: 10.1148/rycan.2021200024

16. 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;11:801876. DOI: 10.3389/fonc.2021.801876

17. Nie D., Wang L., Gao Y. et al. STRAINet: Spatially-varying sTochastic Residual AdversarIal Networks for MRI pelvic organ segmentation. IEEE Trans Neural Networks Learn Syst 2019;30(5):1552–64. DOI: 10.1109/TNNLS.2018.2870182

18. Sanford T.H., Zhang L., Harmon S.A. et al. Data augmentation and transfer learning to improve generalizability of an automated prostate segmentation model. AJR Am J Roentgenol 2020;215(6):1403–10. DOI: 10.2214/AJR.19.22347

19. Liu Q., Dou Q., Yu L. et al. MS-Net: Multi-Site Network for improving prostate segmentation with heterogeneous MRI data. IEEE Trans Med Imaging 2020;39(9):2713–24. DOI: 10.1109/TMI.2020.2974574

20. Wang W., Wang G., Wu X. et al. Automatic segmentation of prostate magnetic resonance imaging using generative adversarial networks. Clin Imaging 2021;70:1–9. DOI: 10.1016/j.clinimag.2020.10.014

21. Aldoj N., Biavati F., Michallek F. et al. Automatic prostate and prostate zones segmentation of magnetic resonance images using DenseNet-like U-net. Sci Reports 2020;10(1):14315. DOI: 10.1038/s41598-020-71080-0

22. Nhat To M.N.N., Vu D.Q., Turkbey B. et al. Deep dense multi-path neural network for prostate segmentation in magnetic resonance imaging. Int J Comput Assist Radiol Surg 2018;13(11):1687–96. DOI: 10.1007/s11548-018-1841-4

23. Zhu Q., Du B., Yan P. Boundary-weighted domain adaptive neural network for prostate MR image segmentation HHS public access. IEEE Trans Med Imaging 2020;39(3):753–63. DOI: 10.1109/TMI.2019.2935018

24. Zhu Y., Wei R., Gao G. et al. Fully automatic segmentation on prostate MR images based on cascaded fully convolution network. J Magn Reson Imaging 2019;49(4):1149–56. DOI: 10.1002/jmri.26337

25. Meyer A., Chlebus G., Rak M. et al. Anisotropic 3D multi-stream CNN for accurate prostate segmentation from multi-planar MRI. Comput Methods Programs Biomed 2021;200:105821. DOI: 10.1016/j.cmpb.2020.105821

26. Geng L., Wang J., Xiao Z. et al. Encoder-decoder with dense dilated spatial pyramid pooling for prostate MR images segmentation. Comput Assist Surg 2019;24(sup2):13–9. DOI: 10.1080/24699322.2019.1649069

27. Chen J., Wan Z., Zhang J. et al. Medical image segmentation and reconstruction of prostate tumor based on 3D AlexNet. Comput Methods Programs Biomed 2021;200:105878. DOI: 10.1016/j.cmpb.2020.105878

28. Yan L., Liu D., Xiang Q. et al. PSP net-based automatic segmentation network model for prostate magnetic resonance imaging. Comput Methods Programs Biomed 2021;207:106211. DOI: 10.1016/j.cmpb.2021.106211

29. Khan S., Vohra S., Farnan L. et al. Using health insurance claims data to assess long-term disease progression in a prostate cancer cohort. Prostate 2022;82(15):1447–55. DOI: 10.1002/pros.24418

30. Toth R., Madabhushi A. Multifeature landmark-free active appearance models: Application to prostate MRI segmentation. IEEE Trans Med Imaging 2012;31(8):1638–50. DOI: 10.1109/TMI.2012.2201498

31. Qiu W., Yuan J., Ukwatta E. et al. Dual optimization based prostate zonal segmentation in 3D MR images. Med Image Anal 2014;18(4):660–73. DOI: 10.1016/j.media.2014.02.009

32. Ghose S., Mitra J., Oliver A. et al. A random forest based classification approach to prostate segmentation in MRI. In: MICCAI Gd. Chall. Prostate MR Image Segmentation, 2012. Pp. 125–128.

33. Rundo L., Militello C., Russo G. et al. Automated prostate gland segmentation based on an unsupervised fuzzy C-means clustering technique using multispectral T1w and T2w MR imaging. Inf 2017;8(2):49. DOI: 10.3390/info8020049

34. Litjens G., Debats O., van de Ven W. et al. A pattern recognition approach to zonal segmentation of the prostate on MRI. Med Image Comput Comput Assist Interv 2012;15(Pt 2):413–20. DOI: 10.1007/978-3-642-33418-4_51

35. Jin J., Zhang L., Leng E. et al. Bayesian spatial models for voxelwise prostate cancer classification using multi-parametric magnetic resonance imaging data. Stat Med 2022;41(3):483–99. DOI: 10.1002/sim.9245

36. Sharma N., Ray A.K., Shukla K.K. et al. Automated medical image segmentation techniques. J Med Phys 2010;35(1):3–14. DOI: 10.4103/0971-6203.58777

37. Chen D., Liu S., Kingsbury P. et al. Deep learning and alternative learning strategies for retrospective real-world clinical data. NPJ Digit Med 2019;2:43. DOI: 10.1038/s41746-019-0122-0

38. Bura V., Caglic I., Snoj Z. et al. MRI features of the normal prostatic peripheral zone: the relationship between age and signal heterogeneity on T2WI, DWI, and DCE sequences. Eur Radiol 2021;31(7):4908–17. DOI: 10.1007/s00330-020-07545-7