Abstract
Surgical segmentation networks can fail silently under acquisition degradation: predicted masks may be wrong even when model confidence remains high. Existing deployment-time monitors rely primarily on uncertainty estimates and can therefore miss confident failures. We present TCSR-Monitor (Temporal Conformal Surgical Risk Monitor), a post-hoc failure-monitoring framework that combines confidence with observable shape, temporal-consistency, and image-quality cues. TCSR-Monitor wraps a frozen segmentation model, requires no model internals, and operates without ground truth at deployment. We also introduce a validation protocol to assess whether alarms remain credible under distribution shift. On EndoVis 2017, leave-one-corruption-out evaluation shows that TCSR-Monitor generalizes to unseen acquisition degradations and substantially outperforms confidence-based baselines. A circularity control confirms that it predicts segmentation failure rather than simply detecting corrupted images. Mondrian conformal calibration balances miss-rates across degradation severities, but a single global threshold still produces false alarms on up to 40% of correctly segmented frames at moderate corruption. Zero-shot transfer to SAM2 demonstrates feature portability, although entropy outperforms the transferred monitor at both evaluated thresholds. Overall, reliable monitoring under acquisition degradation benefits from complementary observable signals beyond confidence alone, but substantial false-alarm and transfer limitations remain. Code and trained configurations are available at github.com/dinhieufam/tcsr-monitor.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/UNSURE2026_038.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: https://papers.miccai.org/miccai-2026-sat/supp/UNSURE2026_038_supp.pdf
Link to Open Review
Open Review Page: https://openreview.net/profile?id=~Hieu_D._Pham1
BibTex
@InProceedings{PhaHie_Beyond_MICCAISAT2026,
author = { Pham, Hieu D. AND Cao, Dang P. M. AND Huynh, Thanh Trung},
title = { { Beyond Uncertainty: Generalizable Failure Monitoring for Surgical Segmentation under Acquisition Degradation } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17260},
month = {pending},
page = {pending}
}