EUVIMEDEUVIMED entdecken
Crossref

Uncertainty-guided model learning for trustworthy medical image segmentation

Qi Ye, Lihua Guo, Qi Wu

Medical & Biological Engineering & Computing · 2026-06 · 64 (6) · 2393-2404

DOI: 10.1007/s11517-026-03591-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, online erschienen am 21.05.2026. Verfasst von Qi Ye und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510640, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Diagnostic Imaging, Machine Learning. Die Arbeit nennt 32 Literaturangaben. Gefördert von: Basic and Applied Basic Research Foundation of Guangdong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although recent AI algorithms have greatly improved accuracy, there is still skepticism among clinicians about the reliability and trustworthiness of these algorithms when used in real-life situations. To address this, our research proposes a new method for trustworthy medical image segmentation, which aims to produce reliable segmentation results and reliable uncertainty estimations without imposing an excessive computational burden. One key feature of our approach is the extraction of feature maps from each decoder and their fusion based on voxel-level uncertainty to leverage multi-scale semantic information fully. We also model the probability and uncertainty of medical image segmentation problems using subjective logic theory, which quantifies the uncertainty of the backbone by modeling class probabilities as a Dirichlet distribution and calculating the distribution strength. Moreover, our framework learns to gather reliable evidence from features, leading to the final segmentation results. To further improve model performance, an uncertainty-based adaptive threshold strategy is designed based on voxel-level uncertainty. This strategy dynamically adjusts the threshold based on the model's learning state, guiding the model to focus on regions with high uncertainty to optimize segmentation results. Extensive experiments on multiple public datasets have validated the effectiveness of our approach, the code is released at https://github.com/SCUT-Ye/UGML .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedDiagnostic ImagingMachine LearningHumansUncertaintyAlgorithms

Stichwörter der Autor:innen

Dirichlet distributionMedical image segmentationUncertainty estimation

Autor:innen und Institutionen

  • School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510640, China.
  • School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510640, China. guolihua@scut.edu.cn.
  • School of Computer Science and Information Technology, The University of Adelaide, ADELAIDE, SA 5005, Australia.

Förderung

  • Basic and Applied Basic Research Foundation of Guangdong Province

Zitieren

APA

Ye, Q., Guo, L., & Wu, Q. (2026). Uncertainty-guided model learning for trustworthy medical image segmentation. Medical & Biological Engineering & Computing, 64(6), 2393-2404. https://doi.org/10.1007/s11517-026-03591-3

Vancouver

Ye Q, Guo L, Wu Q. Uncertainty-guided model learning for trustworthy medical image segmentation. Medical & Biological Engineering & Computing. 2026;64(6):2393-2404. doi:10.1007/s11517-026-03591-3

BibTeX
@article{Ye2026,
  author = {Ye, Qi and Guo, Lihua and Wu, Qi},
  title = {Uncertainty-guided model learning for trustworthy medical image segmentation},
  journal = {Medical & Biological Engineering & Computing},
  year = {2026},
  volume = {64},
  number = {6},
  pages = {2393--2404},
  doi = {10.1007/s11517-026-03591-3}
}
Kostenlos starten →