EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Uncertainty Quantification in Medical Image Segmentation: A Comprehensive Survey

Seyed Sina Ziaee, Katie Ovens

Journal of Imaging · 28.07.2026 · 12 (8) · 341

DOI: 10.3390/jimaging12080341 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Journal of Imaging, online erschienen am 28.07.2026. Verfasst von Seyed Sina Ziaee und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Calgary, 2500 University Dr NW, Calgary, AB T2N 1N4, Canada. Die Arbeit nennt 172 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Uncertainty quantification (UQ) in medical image segmentation is essential for ensuring the reliability and interpretability of deep learning models in clinical decision-making. While convolutional neural networks (CNNs) and transformer-based architectures have achieved remarkable segmentation performance, they often provide deterministic outputs without accounting for uncertainty, which can lead to overconfident predictions in ambiguous cases. This paper presents a comprehensive survey of UQ techniques in medical image segmentation, categorizing existing approaches into Bayesian methods, deep ensembles, deterministic methods, test-time data augmentation, and hybrid models, while treating foundation-model-based UQ as a separate cross-cutting category. We examine key methodologies, including Monte Carlo dropout, Bayesian neural networks, variational inference, and ensemble learning, discussing their advantages and limitations in addressing aleatoric and epistemic uncertainties. Additionally, we explore the clinical relevance of UQ by reviewing its applications in brain tumor segmentation, cardiac imaging, lung nodule detection, and other medical domains. The paper also highlights key evaluation metrics, such as calibration errors, uncertainty–error correlation, and visual interpretability, to assess the effectiveness of UQ methods. Finally, we discuss challenges and future research directions, emphasizing the need for scalable, interpretable, and clinically actionable uncertainty quantification strategies to improve trust in AI-assisted medical image analysis.

Schlagwörter

Stichwörter der Autor:innen

Bayesian methodsMonte Carlo dropoutaleatoric uncertaintydeep ensemblesdeterministic uncertainty methodsepistemic uncertaintyhybrid modelsmedical image segmentationtest-time data augmentationuncertainty quantification

Autor:innen und Institutionen

  • Department of Computer Science, University of Calgary, 2500 University Dr NW, Calgary, AB T2N 1N4, Canada.

Förderung

  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Ziaee, S. S., & Ovens, K. (2026). Uncertainty Quantification in Medical Image Segmentation: A Comprehensive Survey. Journal of Imaging, 12(8), 341. https://doi.org/10.3390/jimaging12080341

Vancouver

Ziaee SS, Ovens K. Uncertainty Quantification in Medical Image Segmentation: A Comprehensive Survey. Journal of Imaging. 2026;12(8):341. doi:10.3390/jimaging12080341

BibTeX
@article{Ziaee2026,
  author = {Ziaee, Seyed Sina and Ovens, Katie},
  title = {Uncertainty Quantification in Medical Image Segmentation: A Comprehensive Survey},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {8},
  pages = {341},
  doi = {10.3390/jimaging12080341}
}
Kostenlos starten →