Uncertainty Quantification and Quality Control for Heatmap-Based Landmark Detection Models
IEEE Transactions on Medical Imaging · 2025
DOI: 10.1109/tmi.2025.3564267 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025. Verfasst von Yong Feng und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: National Natural Science Foundation of China, 111 Project.
Abstract (Originalsprache)
Uncertainty quantification is a vital aspect of explainable artificial intelligence that fosters clinician trust in medical applications and facilitates timely interventions, leading to safer and more reliable outcomes. Although deep learning models have reached clinically acceptable accuracy in anatomical landmark detection, their predictions remain susceptible to contextual noise due to the small size of the target structures, making uncertainty quantification more challenging than in classification and segmentation tasks. This paper presents an end-to-end uncertainty quantification method tailored for heatmap-based anatomical landmark detection models, designed to improve both interpretability and controllability in clinical applications. Leveraging Dempster-Shafer Theory and Subjective Logic Theory, we implement probability assignment and uncertainty quantification through a single forward pass to ensure computational efficiency. We introduce an evidence map that captures the strength of landmark evidence, alongside an uncertainty map that calibrates predicted probabilities within the Subjective Logic framework. The interaction between these two components, facilitated by a cross-attention mechanism, further improves landmark detection accuracy and enhances the effectiveness of uncertainty quantification. Experimental results demonstrate that the proposed method maintains detection accuracy, even in noisy environments, while outperforming state-of-the-art methods in terms of uncertainty quantification and quality control. Furthermore, the model effectively identifies out-of-distribution data solely through calibrated probabilities when encountering inconsistencies in multi-center data and novel data, underscoring its potential for clinical applications. The source code is available at github.com/warmestwind/CalibratedSL.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- 111 Project
Zitieren
APA
Feng, Y., Yang, J., Tang, L., Sun, S., & Wang, Y. (2025). Uncertainty Quantification and Quality Control for Heatmap-Based Landmark Detection Models. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2025.3564267
Vancouver
Feng Y, Yang J, Tang L, Sun S, Wang Y. Uncertainty Quantification and Quality Control for Heatmap-Based Landmark Detection Models. IEEE Transactions on Medical Imaging. 2025. doi:10.1109/tmi.2025.3564267
BibTeX
@article{Feng2025,
author = {Feng, Yong and Yang, Jinzhu and Tang, Lingzhi and Sun, Song and Wang, Yonghuai},
title = {Uncertainty Quantification and Quality Control for Heatmap-Based Landmark Detection Models},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
doi = {10.1109/tmi.2025.3564267}
}
EUVIMED