Metraipolis › archive › dc_db21d260f387
ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-Ultrasound — arXiv:2611.09058
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09058
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:34:47.569Z
- SHA-256 of the archived text
7dd578c9e096b14299093a0414cfd7b802dc134a568b3f3f1cee5280877be3ec- Stable URL of this page
https://metraipolis.com/documento/dc_db21d260f387
How to cite
ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-Ultrasound — arXiv:2611.09058 — arXiv (en), https://arxiv.org/abs/2611.09058 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db21d260f387 (Metraipolis archive dc_db21d260f387, sha256 7dd578c9e096b14299093a0414cfd7b802dc134a568b3f3f1cee5280877be3ec)
BibTeX
@misc{dcdb21d260f387,
title = {ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-Ultrasound — arXiv:2611.09058},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09058},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db21d260f387; sha256 7dd578c9e096b14299093a0414cfd7b802dc134a568b3f3f1cee5280877be3ec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09058. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Purpose: Micro-ultrasound ($\mu$US) 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 $\geq$3), 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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.09058 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:30:47.316Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).