https://doi.org/10.4081/aiua.2026.15673
Artificial Intelligence in equivocal prostatic needle biopsies: benign mimics and cancer detection
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
Published: 7 September 2026
Background: Equivocal prostatic needle biopsies are diagnostically challenging because minute atypical glandular foci may represent early acinar adenocarcinoma or benign mimics. This review critically examines the role of artificial intelligence (AI) in small-focus cancer detection, recognition of benign mimics, and immunohistochemistry (IHC) triage.
Methods: A structured narrative search of PubMed/MEDLINE, Scopus, Web of Science Core Collection, and Google Scholar was conducted from database inception through 15 May 2026. English-language, peer-reviewed diagnostic and validation studies, consensus recommendations, and focused reviews addressing prostate needle-biopsy interpretation, benign mimics, IHC, digital pathology, and clinically relevant AI methods were included.
Results: AI applied to digitized H&E slides can support cancer detection, grading, workflow prioritization, and quality assurance. In equivocal biopsies, its most credible near-term roles are localization of minute suspicious foci and safety-prioritized identification of cases in which IHC might be avoided or requested earlier. However, partial atrophy, adenosis, basal cell hyperplasia, seminal vesicle or ejaculatory duct epithelium, inflammation, treatment effects, and tissue or scanning artefacts may cause clinically important errors. Current evidence is mainly retrospective, and equivocal cases are often defined by previous IHC-ordering practice rather than uniform morphological criteria.
Conclusions: AI may improve the consistency and efficiency of equivocal prostate-biopsy assessment, but it should remain an assistive triage tool. Clinical use requires mimic-enriched external validation, conservative thresholds, interpretable localization, and pathologist-led correlation with morphology and IHC.
Downloads
1. Magi-Galluzzi C. Prostate cancer: diagnostic criteria and role of immunohistochemistry. Mod Pathol. 2018; 31(Suppl 1):S12-S21. DOI: https://doi.org/10.1038/modpathol.2017.139
2. Leone A, Gershman B, Rotker K, et al. Atypical small acinar proliferation (ASAP): is a repeat biopsy necessary ASAP? A multi-institutional review. Prostate Cancer Prostatic Dis. 2016; 19:68-71. DOI: https://doi.org/10.1038/pcan.2015.52
3. Trpkov K. Benign mimics of prostatic adenocarcinoma. Mod Pathol. 2018; 31(Suppl 1):S22-S46. DOI: https://doi.org/10.1038/modpathol.2017.136
4. Herawi M, Parwani AV, Irie J, Epstein JI. Small glandular proliferations on needle biopsies: most common benign mimickers of prostatic adenocarcinoma sent in for expert second opinion. Am J Surg Pathol. 2005; 29:874-880. DOI: https://doi.org/10.1097/01.pas.0000159520.36806.3e
5. Epstein JI, Egevad L, Humphrey PA, Montironi R; Members of the ISUP Immunohistochemistry in Diagnostic Urologic Pathology Group. Best practices recommendations in the application of immunohistochemistry in the prostate: report from the International Society of Urologic Pathology Consensus Conference. Am J Surg Pathol. 2014; 38:e6-e19. DOI: https://doi.org/10.1097/PAS.0000000000000238
6. Mandel P, Wenzel M, Hoeh B, et al. Immuno-histochemistry for prostate biopsy—impact on histological prostate cancer diagnoses and clinical decision making. Curr Oncol. 2021; 28:2123-2133. DOI: https://doi.org/10.3390/curroncol28030197
7. Campanella G, Hanna MG, Geneslaw L, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole-slide images. Nat Med. 2019; 25:1301-1309. DOI: https://doi.org/10.1038/s41591-019-0508-1
8. Ström P, Kartasalo K, Olsson H, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study. Lancet Oncol. 2020; 21:222-232. DOI: https://doi.org/10.1016/S1470-2045(19)30738-7
9. 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 Health. 2020; 2:e407-e416. DOI: https://doi.org/10.1016/S2589-7500(20)30159-X
10. Bulten W, Kartasalo K, Chen PHC, et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat Med. 2022;28:154-163. DOI: https://doi.org/10.1016/S0302-2838(22)00693-5
11. Srigley JR. Benign mimickers of prostatic adenocarcinoma. Mod Pathol. 2004; 17:328-348. DOI: https://doi.org/10.1038/modpathol.3800055
12. Cheville JC, Bostwick DG. Postatrophic hyperplasia of the prostate. A histologic mimic of prostatic adenocarcinoma. Am J Surg Pathol. 1995; 19:1068-1076. DOI: https://doi.org/10.1097/00000478-199509000-00011
13. Epstein JI. Adenosis of the prostate. Histopathology. 1995; 27:379-380. doi not available.
14. Arista-Nasr J, Martinez-Benitez B, Viveros-Contreras C, et al. Seminal epithelium in prostate biopsy can mimic malignant and premalignant prostatic lesions. Actas Urol Esp. 2016; 40:17-22. DOI: https://doi.org/10.1016/j.acuroe.2015.11.009
15. Humphrey PA. Histopathology of prostate cancer. Cold Spring Harb Perspect Med. 2017; 7:a030411. DOI: https://doi.org/10.1101/cshperspect.a030411
16. Jiang Z, Woda BA, Rock KL, et al. Using an AMACR/ P504S/34βE12/p63 cocktail for the detection of small focal prostate carcinoma in needle biopsy specimens. Am J Clin Pathol. 2005; 123:231-236. DOI: https://doi.org/10.1309/1G1NK9DBGFNB792L
17. Brimo F, Epstein JI. Immunohistochemical pitfalls in prostate pathology. Hum Pathol. 2012; 43:313-324. DOI: https://doi.org/10.1016/j.humpath.2011.11.005
18. Raciti P, Sue J, Ceballos R, et al. Novel artificial intelligence system increases the detection of prostate cancer in whole-slide images of core needle biopsies. Mod Pathol. 2020; 33:2058-2066. DOI: https://doi.org/10.1038/s41379-020-0551-y
19. 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; 34:1588-1595. DOI: https://doi.org/10.1038/s41379-021-00794-x
20. Eloy C, Marques A, Pinto J, et al. Artificial intelligence-assisted cancer diagnosis improves the efficiency of pathologists in prostatic biopsies. Virchows Arch. 2023; 482:595-604. DOI: https://doi.org/10.1007/s00428-023-03518-5
21. Nateghi R, Zhou R, Saft M, et al. AI-driven screening of equivocal prostate IHC cases: development and validation of a screening and cancer detection framework. Mod Pathol. 2025; 38:100904. DOI: https://doi.org/10.1016/j.modpat.2025.100904
22. Chatrian A, Colling RT, Browning L, et al. Artificial intelligence for advance requesting of immunohistochemistry in diagnostically uncertain prostate biopsies. Mod Pathol. 2021; 34:1780-1794. DOI: https://doi.org/10.1038/s41379-021-00826-6
23. Blilie A, Mulliqi N, Ji X, et al. Artificial intelligence-assisted prostate cancer diagnosis for reduced use of immunohistochemistry. Commun Med (Lond). 2025; 5:425. DOI: https://doi.org/10.1038/s43856-025-01185-y
24. Gadermayr M, Tschuchnig M. Multiple instance learning for digital pathology: a review of the state-of-the-art, limitations and future potential. Comput Med Imaging Graph. 2024; 112:102337. DOI: https://doi.org/10.1016/j.compmedimag.2024.102337
25. Chen RJ, Ding T, Lu MY, et al. Towards a general-purpose foundation model for computational pathology. Nat Med. 2024; 30:850-862. DOI: https://doi.org/10.1038/s41591-024-02857-3
26. Filiot A, Ghermi R, Olivier A, et al. Scaling self-supervised learning for histopathology with masked image modeling. Med Image Anal. 2024; 91:103013. DOI: https://doi.org/10.1101/2023.07.21.23292757
27. U.S. Food and Drug Administration. De Novo classification request for Paige Prostate (DEN200080). Decision date: September 21, 2021. Accessed May 15, 2026.
Supporting Agencies
Data Availability Statement
Aviable from the corresponding author upon a reasonable request
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.