cs.CVNov 6, 2026

ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-Ultrasound

Authors: Mohammad Mahdi Abootorabi, Nooshin Maghsoodi, Armin Saadat, Obed Dzikunu, Zhuoxin Guo, Hannes Cash, Ferdinand Luger, Adam Kinnaird, 

Organizations: The University of British Columbia, Vancouver, BC, Canada. · Vector Institute, Toronto, ON, Canada. · Queen’s University, Kingston, ON, Canada. · ProUro, Berlin, Germany. · 

Abstract

Purpose: Micro-ultrasound (μμUS) is a promising modality for prostate cancer (PCa) detection, but identifying suspicious tissue depends heavily on clinical experience. Models trained on sparse, noisy core-level pathology offer little insight into their decisions and can fail under domain shift. Clinical use needs a traceable decision process and a flag for uncertain predictions. Methods: We introduce ProtoCouncil, in which three foundation encoders (MedSAM, DINOv3 and V-JEPA 2.1) learn case-based prototypes at three anatomical levels: whole gland, needle track and gland sectors. Prototypes are projected onto real training-core regions, and label-free fusion keeps every class logit as a bias plus an exact sum of prototype similarity contributions. Encoder disagreement triggers selective prediction. Results: In five-fold patient-level cross-validation (6,588 cores, 693 patients), ProtoCouncil reaches 82.9% AUROC for clinically significant PCa (csPCa, Grade Group ≥\geq3), 4.3 points above the best previously published method. In zero-shot evaluation on two external cohorts, ProtoCouncil achieves higher all-cancer and csPCa AUROC than all previous methods. Nearest same-class exemplars match test-core tumor involvement better than random same-class cases. Externally, csPCa accuracy falls from 79% when encoders agree to 27% when two oppose the fused call. Abstaining on disagreement raises balanced accuracy by 7 and 15 points, while retaining 58% and 54% of the cores. Conclusion: ProtoCouncil grounds core-level predictions in exact similarity-based evidence from real, anatomically indexed training cases, which makes its reasoning interpretable. It achieves the highest csPCa AUROC across three cohorts and identifies unreliable predictions through encoder disagreement.

Figures & tables

Explore similar work

CardsList
  1. Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection

    Jun 29, 2026Mohammad Mahdi Abootorabi, Sina Namazi, Armin Saadat +7Medical Image LocalizationReinforcement Learning

  2. GUIDE-US: Grade-Informed Unpaired Distillation of Encoder Knowledge from Histopathology to Micro-UltraSound

    Feb 22, 2026Emma Willis, Tarek Elghareb, Paul F. R. Wilson +6Ultrasound Image ClassificationProstate Cancer Grading