arXiv:2608. 03342v1 Announce Type: cross Abstract: Conditional segmentation models may be trained and evaluated with auxiliary signals cleaner than those available at deployment.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2608. 10903v1 Announce Type: cross Abstract: Reliable clinical deployment of machine learning requires models that know when they are likely to fail, particularly for subgroups underrepresented in training data.
arXiv:2609.18256v1 Announce Type: new Abstract: Reliability under sparse and heterogeneous failures remains a fundamental challenge for medical image segmentation. High average accuracy can conceal a...
arXiv:2607. 05008v1 Announce Type: cross Abstract: Echocardiography is the first imaging modality used for assessing cardiac function, and accurate segmentation of cardiac structures is essential for deriving biomarkers.
The paper introduces the "segmentation ceiling," a quantitative criterion that determines when explicit left‑ventricular (LV) segmentation can improve ejection fraction (EF) regression. By deriving how per‑frame segmentation area error propagates into EF error, the authors find that a break‑even error of about 10% per frame is required, whereas typical segmenters exceed this threshold (~14%). Consequently, several strategies that incorporate segmentation or area information fail to outperform a raw‑video baseline, while techniques such as weight averaging with strong augmentation and a heteroscedastic beta‑NLL loss yield competitive EF predictions and well‑calibrated uncertainty estimates.
arXiv:2609.21412v1 Announce Type: new Abstract: Medical image segmenters often get worse when sites, scanner vendors, or protocols change. Continual test-time adaptation (CTTA) addresses this problem...
arXiv:2605. 16427v2 Announce Type: replace-cross Abstract: Deep learning models for echocardiography segmentation often struggle to generalise across institutions, scanners, and patient populations, where collecting large, consistently annotated datasets is infeasible.