Coarse for Fine: Bounding Box Supervised Thyroid Ultrasound Image Segmentation Using Spatial Arrangement and Hierarchical Prediction Consistency
Date
2025
Authors
Chi, Jianning
Lin, Geng
Li, Zelan
Zhang, Wenjun
Chen, Jia-hui
Huang, Ying
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE Journal of Biomedical and Health Informatics
ORCID
Type
Preprint
Degree Level
Abstract
Weakly-supervised learning methods have become increasingly attractive for medical image segmentation, but suffered from a high dependence on quantifying the pixel-wise affinities of low-level features, which are easily corrupted in thyroid ultrasound images, resulting in segmentation over-fitting to weakly annotated regions without precise delineation of target boundaries. We propose a dual-branch weakly-supervised learning framework to optimize the backbone segmentation network by calibrating semantic features into rational spatial distribution under the indirect, coarse guidance of the bounding box mask. Specifically, in the spatial arrangement consistency branch, the maximum activations sampled from the preliminary segmentation prediction and the bounding box mask along the horizontal and vertical dimensions are compared to measure the rationality of the approximate target localization. In the hierarchical prediction consistency branch, the target and background prototypes are encapsulated from the semantic features under the combined guidance of the preliminary segmentation prediction and the bounding box mask. The secondary segmentation prediction induced from the prototypes is compared with the preliminary prediction to quantify the rationality of the elaborated target and background semantic feature perception. Experiments on three thyroid datasets illustrate that our model outperforms existing weakly-supervised methods for thyroid gland and nodule segmentation and is comparable to the performance of fully-supervised methods with reduced annotation time. The proposed method has provided a weakly-supervised segmentation strategy by simultaneously considering the target's location and the rationality of target and background semantic features distribution. It can improve the applicability of deep learning based segmentation in the clinical practice. The source code and relative datasets will be available at https://github.com/LanLanUp/SAHP-Net.
Description
This article has been accepted for publication in IEEE Journal of Biomedical and Health Informatics. This is the author's version which has not been fully edited and content may change prior to final publication. Citation information: https://doi.org/10.1109/JBHI.2025.3535541
Copyright may be transferred without notice, after which this version may no longer be accessible.
Keywords
Image segmentation, Thyroif, Ultrasonic imaging, Semantics, Annotations, Feature extraction, Prototypes, Medical diagnostic imaging, Anatomy, Noise
Citation
Chi, J., Lin, G., Li, Z., Zhang, W., Chen, J., & Huang, Y. (2025). Coarse for Fine: Bounding Box Supervised Thyroid Ultrasound Image Segmentation Using Spatial Arrangement and Hierarchical Prediction Consistency. IEEE Journal of Biomedical and Health Informatics, 1–14. https://doi.org/10.1109/JBHI.2025.3535541
Degree
Department
Program
Advisor
Committee
Part Of
item.page.relation.ispartofseries
DOI
https://doi.org/10.1109/JBHI.2025.3535541