Calibrating on Medical Segmentation Model through Signed Distance

Files

hdl_149262.pdf (6.71 MB)
  (Published version)

Date

2025

Authors

Liang, W.
Zhang, W.E.
Yue, L.
Xu, M.
Maennel, O.
Chen, W.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025, pp.1778-1787

Statement of Responsibility

Wenhao Liang, Wei Emma Zhang, Lin Yue, Miao Xu, Olaf Maennel and Weitong Chen

Conference Name

ACM International Conference on Information and Knowledge Management (CIKM) (10 Nov 2025 - 14 Nov 2025 : Seoul)

Abstract

Classical overlap metrics such as Dice or IoU quantify where a medical-image segmentation falls short but say nothing about the confidence of each prediction. Over-confident errors are particularly dangerous in clinical practice, where a single false-positive voxel may trigger an unnecessary biopsy. We introduce three contributions that jointly address spatial precision and reliability. (i) Signed-Distance Calibration (SDC) loss couples cross-entropy, local calibration and a differentiable signed-distance penalty, enforcing boundary accuracy while moderating confidence. (ii) A Spatially Adaptive Margin (SAM) module applies lightweight morphological transforms to ground-truth masks before computing the local target, sharpening ambiguous edges. (iii) Pixel-wise Expected Calibration Error (pECE) extends ECE to millions of voxels and penalises high-confidence false positives. Across four public datasets (ACDC, FLARE, BraTS, PROSTATE) and two back-bones (U-Net, nnU-Net), SDC improves Dice by up to 4 percentage points and halves ECE compared with the state of the art, without sacrificing runtime.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2025 Copyright held by the owner/author(s). This is an open access article

License

Call number

Persistent link to this record