Metraipolis › archive › dc_6a49747ef9be

TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening — arXiv:2609.00300

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00300
License (as archived)
CC0-1.0
Archived
2026-10-17T06:52:29.325Z
SHA-256 of the archived text
72f639cae6d3d93cdce9a777d53535be8ec6489cd3d99b08d81a6da0bde12267
Stable URL of this page
https://metraipolis.com/documento/dc_6a49747ef9be

How to cite

TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening — arXiv:2609.00300 — arXiv (en), https://arxiv.org/abs/2609.00300 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6a49747ef9be (Metraipolis archive dc_6a49747ef9be, sha256 72f639cae6d3d93cdce9a777d53535be8ec6489cd3d99b08d81a6da0bde12267)
BibTeX
@misc{dc6a49747ef9be,
  title = {TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening — arXiv:2609.00300},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00300},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6a49747ef9be; sha256 72f639cae6d3d93cdce9a777d53535be8ec6489cd3d99b08d81a6da0bde12267},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00300. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reducing the review of clearly cancer-negative screening mammograms could lower radiologist workload without compromising cancer detection. We propose a closed-loop threshold-aware training strategy in which the dismissal threshold is recalculated during training and used to penalize cancer-positive images that approach the dismissal region. We evaluated the method on NLBS and RSNA using five controlled training configurations, with case-level assessment based on a one-sided 99\% Clopper--Pearson upper bound for cancer prevalence among dismissed cases. The proposed model achieved the highest case-level dismissal rates at both 98\% and 95\% recall targets. On NLBS, dismissal reached 19.74\% and 21.70\%, while the cross-entropy baseline did not meet either recall target. On RSNA, dismissal improved from 7.04\% to 14.31\% and from 13.49\% to 19.69\%. In external RSNA$\to$NLBS evaluation, the proposed model achieved dismissal rates of 12.95\% and 19.87\% at the 98\% and 95\% recall targets, respectively. These results support closed-loop threshold-aware training for high-recall selective dismissal.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.00300 — 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 2026-10-17T06:41:55.882Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).