Difficulties and Recommendations for AI-Based Prediction of Prostate Cancer Aggressiveness in Digital Pathology
Main Article Content
Abstract
Prostate cancer is among the most common cancers in men with around 1.4 million new cases each year world-wide. A vital part in the diagnosis of prostate cancer is the evaluation of its severity using biopsies and histopathology. Recent progress in artificial intelligence-based image analysis has led to a flurry of algorithms for the automated analysis of prostate cancer histopathological data focusing on the detection of cancerous areas, the grading of cancer severity, and patient outcome. Some of these approaches have reached human expert-level performance and digital models trained directly on patient outcomes might surpass human performance in the future.
Although these results hold great promise for the future usage of digital pathology in clinical settings, several bottlenecks remain to be addressed. Especially the robustness, reliability and trustworthiness of predictions must be guaranteed across a wide range of variation in protocols and instrumentation. While human experts are relatively robust to technical and biological variation in biopsies, artificial intelligence-based systems tend to struggle with differences in staining intensity, color, scanner type, and image resolution, impeding the clinical usage of digital models.
In this work we highlight salient problems and minimal requirements of computational pathology for future use in clinical settings, while focusing on prostate cancer as a use case. In particular, we highlight data and model problems and solutions that include data variability, dataset size, and data annotations, as well as model robustness to data heterogeneity, model prediction confidence, and the explainability of model decisions. While model and data requirements for successful computational pathology in clinics will be highlighted, legal, ethical, and deployment requirements will not be addressed in this review.
In summary, we provide a short overview of the field, salient problems, and potential solutions to harvest the full potential of digital pathology for prostate cancer in clinical practice.
Article Details
The Medical Research Archives grants authors the right to publish and reproduce the unrevised contribution in whole or in part at any time and in any form for any scholarly non-commercial purpose with the condition that all publications of the contribution include a full citation to the journal as published by the Medical Research Archives.
References
2. Gleason DF. Classification of prostatic carcinomas. Cancer Chemother Rep. 1966;50(3):125-128. https://cir.nii.ac.jp/crid/1573105974852230656. Accessed September 7, 2023.
3. Mellinger GT, Gleason D, Bailar J. The histology and prognosis of prostatic cancer. J Urol. 1967;97(2):331-337. doi:10.1016/S0022-5347(17)63039-8
4. Epstein JI, Allsbrook WC, Amin MB, et al. The 2005 International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma. Am J Surg Pathol. 2005;29(9):1228-1242. doi:10.1097/01.PAS.0000173646.99337.B1
5. Sethi A, Sha L, Vahadane AR, et al. Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images. J Pathol Inform. 2016;7(1):17. doi:10.4103/2153-3539.179984
6. Bulten W, Pinckaers H, van Boven H, et al. Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study. Lancet Oncol. 2020;21(2):233-241. doi:10.1016/S1470-2045(19)30739-9
7. Nagpal K, Foote D, Tan F, et al. Development and Validation of a Deep Learning Algorithm for Gleason Grading of Prostate Cancer From Biopsy Specimens. JAMA Oncol. 2020;6(9):1372-1380. doi:10.1001/JAMAONCOL.2020.2485
8. Pantanowitz L, Quiroga-Garza GM, Bien L, et al. An artificial intelligence algorithm for prostate cancer diagnosis in whole slide images of core needle biopsies: a blinded clinical validation and deployment study. Lancet Digit Heal. 2020;2(8):e407-e416. doi:10.1016/S2589-7500(20)30159-X
9. Li W, Li J, Sarma K V., et al. Path R-CNN for Prostate Cancer Diagnosis and Gleason Grading of Histological Images. IEEE Trans Med Imaging. 2019;38(4):945-954. doi:10.1109/TMI.2018.2875868
10. Ren J, Sadimin E, Foran DJ, Qi X. Computer aided analysis of prostate histopathology images to support a refined Gleason grading system. Proc SPIE--the Int Soc Opt Eng. 2017;10133:101331V. doi:10.1117/12.2253887
11. Bulten W, Bándi P, Hoven J, et al. Epithelium segmentation using deep learning in H&E-stained prostate specimens with immunohistochemistry as reference standard. Sci Rep. 2019;9(1). doi:10.1038/S41598-018-37257-4
12. Bukowy JD, Foss H, McGarry SD, et al. Accurate segmentation of prostate cancer histomorphometric features using a weakly supervised convolutional neural network. J Med imaging (Bellingham, Wash). 2020;7(5). doi:10.1117/1.JMI.7.5.057501
13. Rabilloud N, Allaume P, Acosta O, et al. Deep Learning Methodologies Applied to Digital Pathology in Prostate Cancer: A Systematic Review. Diagnostics. 2023;13(16):2676. doi:10.3390/DIAGNOSTICS13162676/S1
14. Campanella G, Hanna MG, Geneslaw L, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med. 2019;25(8):1301. doi:10.1038/S41591-019-0508-1
15. Li Y, Huang M, Zhang Y, et al. Automated Gleason Grading and Gleason Pattern Region Segmentation Based on Deep Learning for Pathological Images of Prostate Cancer. IEEE Access. 2020;8:117714-117725. doi:10.1109/ACCESS.2020.3005180
16. Arvaniti E, Fricker KS, Moret M, et al. Automated Gleason grading of prostate cancer tissue microarrays via deep learning. Sci Reports 2018 81. 2018;8(1):1-11. doi:10.1038/s41598-018-30535-1
17. TH N, S S, V M, et al. Automatic Gleason grading of prostate cancer using quantitative phase imaging and machine learning. J Biomed Opt. 2017;22(3):036015. doi:10.1117/1.JBO.22.3.036015
18. Bulten W, Kartasalo K, Chen PHC, et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat Med 2022 281. 2022;28(1):154-163. doi:10.1038/s41591-021-01620-2
19. Sandeman K, Blom S, Koponen V, et al. AI Model for Prostate Biopsies Predicts Cancer Survival. Diagnostics (Basel, Switzerland). 2022;12(5). doi:10.3390/DIAGNOSTICS12051031
20. Perincheri S, Levi AW, Celli R, et al. An independent assessment of an artificial intelligence system for prostate cancer detection shows strong diagnostic accuracy. Mod Pathol. 2021;34(8):1588-1595. doi:10.1038/S41379-021-00794-X
21. Jung M, Jin MS, Kim C, et al. Artificial intelligence system shows performance at the level of uropathologists for the detection and grading of prostate cancer in core needle biopsy: an independent external validation study. Mod Pathol. 2022;35(10):1449-1457. doi:10.1038/S41379-022-01077-9
22. Tellez D, Litjens G, Bándi P, et al. Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology. Med Image Anal. 2019;58:101544. doi:10.1016/J.MEDIA.2019.101544
23. Macenko M, Niethammer M, Marron JS, et al. A method for normalizing histology slides for quantitative analysis. Proc - 2009 IEEE Int Symp Biomed Imaging From Nano to Macro, ISBI 2009. 2009:1107-1110. doi:10.1109/ISBI.2009.5193250
24. Reinhard E, Ashikhmin M, Gooch B, Shirley P. Color transfer between images. IEEE Comput Graph Appl. 2001;21(5):34-41. doi:10.1109/38.946629
25. Khan AM, Rajpoot N, Treanor D, Magee D. A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution. IEEE Trans Biomed Eng. 2014;61(6):1729-1738. doi:10.1109/TBME.2014.2303294
26. Zhu JY, Park T, Isola P, Efros AA. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proc IEEE Int Conf Comput Vis. 2017;2017-October:2242-2251. doi:10.1109/ICCV.2017.244
27. Rieke N, Hancox J, Li W, et al. The future of digital health with federated learning. NPJ Digit Med. 2020;3(1). doi:10.1038/S41746-020-00323-1
28. Wolff J, Matschinske J, Baumgart D, et al. Federated machine learning for a facilitated implementation of Artificial Intelligence in healthcare - a proof of concept study for the prediction of coronary artery calcification scores. J Integr Bioinform. 2022;19(4). doi:10.1515/JIB-2022-0032
29. Narmadha K, Varalakshmi P. Federated Learning in Healthcare: A Privacy Preserving Approach. Stud Health Technol Inform. 2022;294:194-198. doi:10.3233/SHTI220436
30. Xue Y, Ye J, Zhou Q, et al. Selective synthetic augmentation with HistoGAN for improved histopathology image classification. Med Image Anal. 2021;67:101816. doi:10.1016/J.MEDIA.2020.101816
31. Li W, Li J, Polson J, Wang Z, Speier W, Arnold C. High resolution histopathology image generation and segmentation through adversarial training. Med Image Anal. 2022;75:102251. doi:10.1016/J.MEDIA.2021.102251
32. Li J, Ettel M, Amin A, et al. Interobserver Reproducibility of Quantifying Gleason Pattern 4 Cancer in Prostate Biopsy: Implications for Clinical Practice. http://www.xiahepublishing.com/. 2023;3(1):4-9. doi:10.14218/JCTP.2022.00026
33. Veltri RW, Marlow C, Khan MA, Miller MC, Epstein JI, Partin AW. Significant variations in nuclear structure occur between and within Gleason grading patterns 3, 4, and 5 determined by digital image analysis. Prostate. 2007;67(11):1202-1210. doi:10.1002/PROS.20614
34. Olsson H, Kartasalo K, Mulliqi N, et al. Estimating diagnostic uncertainty in artificial intelligence assisted pathology using conformal prediction. Nat Commun 2022 131. 2022;13(1):1-10. doi:10.1038/s41467-022-34945-8
35. Wilm F, Marzahl C, Breininger K, Aubreville M. Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics). 2022;13166 LNCS:5-13. doi:10.1007/978-3-030-97281-3_1/FIGURES/4
36. Lafarge MW, Pluim JPW, Eppenhof KAJ, Moeskops P, Veta M. Domain-Adversarial Neural Networks to Address the Appearance Variability of Histopathology Images. In: Cardoso MJ, Arbel T, Carneiro G, et al., eds. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Cham: Springer International Publishing; 2017:83-91.
37. Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nat Med 2022 281. 2022;28(1):31-38. doi:10.1038/s41591-021-01614-0
38. Ozkan TA, Eruyar AT, Cebeci OO, Memik O, Ozcan L, Kuskonmaz I. Interobserver variability in Gleason histological grading of prostate cancer. new pub Med Journals Sweden AB. 2016;50(6):420-424. doi:10.1080/21681805.2016.1206619
39. Dietrich E, Fuhlert P, Ernst A, et al. Towards Explainable End-to-End Prostate Cancer Relapse Prediction from H&E Images Combining Self-Attention Multiple Instance Learning with a Recurrent Neural Network. Proc Mach Learn Res. 2021;158:38-53. https://proceedings.mlr.press/v158/dietrich21a.html. Accessed September 7, 2023.
40. Walhagen P, Bengtsson E, Lennartz M, Sauter G, Busch C. AI-based prostate analysis system trained without human supervision to predict patient outcome from tissue samples. J Pathol Inform. 2022;13:100137. doi:10.1016/J.JPI.2022.100137