Pathologist-like explainable AI for interpretable Gleason grading in prostate cancer
Open Access
- 8 October 2025
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-17
Abstract
The aggressiveness of prostate cancer is primarily assessed from histopathological data using the Gleason scoring system. Conventional artificial intelligence (AI) approaches can predict Gleason scores, but often lack explainability, which may limit clinical acceptance. Here, we present an alternative, inherently explainable AI that circumvents the need for post-hoc explainability methods. The model was trained on 1,015 tissue microarray core images, annotated with detailed pattern descriptions by 54 international pathologists following standardized guidelines. It uses pathologist-defined terminology and was trained using soft labels to capture data uncertainty. This approach enables robust Gleason pattern segmentation despite high interobserver variability. The model achieved comparable or superior performance to direct Gleason pattern segmentation (Dice score: $${0.713}_{\pm 0.003}$$ vs. $${0.691}_{\pm 0.010}$$ ) while providing interpretable outputs. We release this dataset to encourage further research on segmentation in medical tasks with high subjectivity and to deepen insights into pathologists’ reasoning.
Keywords
All Related Versions
This publication has 51 references indexed in Scilit:
- Automatic grading of prostate cancer in digitized histopathology images: Learning from multiple expertsMedical Image Analysis, 2018
- A curated collection of tissue microarray images and clinical outcome data of prostate cancer patientsScientific Data, 2017
- The evolving Gleason grading system2016
- The 2014 International Society of Urological Pathology (ISUP) Consensus Conference on Gleason Grading of Prostatic CarcinomaAmerican Journal of Surgical Pathology, 2016
- Diagnosis of “Poorly Formed Glands” Gleason Pattern 4 Prostatic Adenocarcinoma on Needle BiopsyAmerican Journal of Surgical Pathology, 2015
- Diagnosis of Gleason Pattern 5 Prostate Adenocarcinoma on Core Needle BiopsyAmerican Journal of Surgical Pathology, 2015
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- Interobserver reproducibility of Gleason grading: evaluation using prostate cancer tissue microarraysJournal of Cancer Research and Clinical Oncology, 2008
- Simultaneous Truth and Performance Level Estimation (STAPLE): An Algorithm for the Validation of Image SegmentationIEEE Transactions on Medical Imaging, 2004
- The Measurement of Observer Agreement for Categorical DataBiometrics, 1977