aiqbench analysis
SegWithU introduces a novel post-hoc framework that models uncertainty as perturbation energy within frozen segmentation backbones, enabling efficient single-forward-pass reliability assessment without retraining the core model. By generating distinct maps for calibration and error ranking across major medical imaging datasets like BraTS2024, this approach offers a practical pathway to integrating risk-aware decision support into clinical workflows. The method demonstrates that lightweight uncertainty heads can effectively complement existing pretrained architectures while maintaining high segmentation fidelity.
SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation
arXiv:2604.15271v4 Announce Type: replace-cross Abstract: Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decision support. Many strong uncertainty methods require repeated inference, while efficient single-forward-pass alternatives often provide weaker failure ranking or rely on restrictive feature-space assumptions. We present $\textbf{SegWithU}$, a post-hoc framework that augments a frozen pretrained segmentation backbone with a lightweight uncertainty head. SegWithU taps intermediate backbone features and models uncertainty as perturbation energy in a compact probe space using rank-1 posterior probes. It produces two voxel-wise uncertainty maps: a calibration-oriented map for probability tempering and a ranking-oriented map for error detection and selective prediction. Across ACDC, BraTS2024, and LiTS, SegWithU is the strongest and most consistent single-forward-pass baseline, achieving AUROC/AURC of $0.9838/2.4885$, $0.9946/0.2660$, and $0.9925/0.8193$, respectively, while preserving segmentation quality. These results suggest that perturbation-based uncertainty modeling is an effective and practical route to reliability-aware medical segmentation. Source code is available at https://github.com/ProjectNeura/SegWithU.
Abstract:Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decision support. Many strong uncertainty methods require repeated inference, while efficient single-forward-pass alternatives often provide weaker failure ranking or rely on restrictive feature-space assumptions. We present $\textbf{SegWithU}$, a post-hoc framework that augments a frozen pretrained segmentation backbone with a lightweight uncertainty head. SegWithU taps intermediate backbone features and models uncertainty as perturbation energy in a compact probe space using rank-1 posterior probes. It produces two voxel-wise uncertainty maps: a calibration-oriented map for probability tempering and a ranking-oriented map for error detection and selective prediction. Across ACDC, BraTS2024, and LiTS, SegWithU is the strongest and most consistent single-forward-pass baseline, achieving AUROC/AURC of $0.9838/2.4885$, $0.9946/0.2660$, and $0.9925/0.8193$, respectively, while preserving segmentation quality. These results suggest that perturbation-based uncertainty modeling is an effective and practical route to reliability-aware medical segmentation. Source code is available at this https URL.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2604.15271 [cs.CV]
(or arXiv:2604.15271v4 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2604.15271 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 253 words
Related coverage
Stock Market Today Highlights, Sept 2: Sensex ends 373 pts lower at 76, 570, Nifty below 24, 000; Asian Paints, HDFC Bank fall most
thehindubusinessline.com · Sep 2, 2026
Links #3: 2026/06 Part 1
LessWrong · Jun 15, 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · Sep 23, 2026
Lattice-Based Cryptography Explained
Quantum Zeitgeist · Aug 15, 2026