Coarse for Fine: Bounding Box Supervised Thyroid Ultrasound Image Segmentation Using Spatial Arrangement and Hierarchical Prediction Consistency

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 t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE journal of biomedical and health informatics Ročník 29; číslo 6; s. 4186 - 4199
Hlavní autoři: Chi, Jianning, Lin, Geng, Li, Zelan, Zhang, Wenjun, Chen, Jia-hui, Huang, Ying
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.06.2025
Témata:
Algorithms
Anatomy
Annotations
bounding box annotation
Databases, Factual
Feature extraction
hierarchical prediction consistency
Humans
Image Interpretation, Computer-Assisted - methods
Image segmentation
Medical diagnostic imaging
Noise
Prototypes
semantic prototype
Semantics
Supervised Machine Learning
Thyroid
Thyroid Gland - diagnostic imaging
Thyroid ultrasound image segmentation
Ultrasonic imaging
Ultrasonography - methods
weakly-supervised learning
ISSN:2168-2194, 2168-2208, 2168-2208
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2168-2194
2168-2208
2168-2208
DOI:10.1109/JBHI.2025.3535541