Weakly-supervised thyroid ultrasound segmentation: Leveraging multi-scale consistency, contextual features, and bounding box supervision for accurate target delineation

Weakly-supervised learning (WSL) methods have gained significant attention in medical image segmentation, but they often face challenges in accurately delineating boundaries due to overfitting to weak annotations such as bounding boxes. This issue is particularly pronounced in thyroid ultrasound ima...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers in biology and medicine Ročník 186; s. 109669
Hlavní autor: Aly, Mohammed
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Elsevier Ltd 01.03.2025
Elsevier Limited
Témata:
Accuracy
Algorithms
Annotations
Bounding box supervision
Boxes
Contextual feature integration
Datasets
Deep learning
Delineation
Feature maps
Humans
Image annotation
Image processing
Image Processing, Computer-Assisted - methods
Image segmentation
Internal Medicine
Localization
Medical imaging
Methods
Modules
Multi-scale consistency
Other
Performance evaluation
Predictions
Prototypes
Semantics
Supervised learning
Supervised Machine Learning
Supervision
Thyroid
Thyroid gland
Thyroid Gland - diagnostic imaging
Thyroid ultrasound segmentation
Ultrasonic imaging
Ultrasonography - methods
Ultrasound
Weakly-supervised learning
Multi-scale consistency
Weakly-supervised learning
Thyroid ultrasound segmentation
Bounding box supervision
Contextual feature integration
ISSN:0010-4825, 1879-0534, 1879-0534
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Weakly-supervised learning (WSL) methods have gained significant attention in medical image segmentation, but they often face challenges in accurately delineating boundaries due to overfitting to weak annotations such as bounding boxes. This issue is particularly pronounced in thyroid ultrasound images, where low contrast and noisy backgrounds hinder precise segmentation. In this paper, we propose a novel weakly-supervised segmentation framework that addresses these challenges. Our framework integrates several key components: the Spatial Arrangement Consistency (SAC) branch, the Hierarchical Prediction Consistency (HPC) branch, the Contextual Feature Integration (CFI) branch, and the Multi-scale Prototype Refinement (MPR) module. These elements work together to enhance segmentation performance and mitigate overfitting to bounding box annotations. Specifically, the SAC branch ensures spatial alignment of the predicted segmentation with the target by evaluating maximum activations along both the horizontal and vertical dimensions of the bounding box. The HPC branch refines prototypes for target and background regions from semantic feature maps, comparing secondary predictions with the initial ones to improve segmentation accuracy. The CFI branch enhances feature representation by incorporating contextual information from neighboring regions, while the MPR module further refines segmentation accuracy by balancing global context and local details through multi-scale feature refinement. We evaluate the performance of our method on two thyroid ultrasound datasets: TG3K and TN3K, using comprehensive metrics including mIOU, DSC, HD95, DI, ACC, PR, and SE. On the TG3K dataset, the Proposed Method achieved mIOU of 71.85 %, DSC of 85.92 %, HD95 of 13.09 mm, and ACC of 0.93, significantly outperforming existing weakly-supervised methods. On the TN3K dataset, our model demonstrated mIOU of 70.45 %, DSC of 84.81 %, HD95 of 14.16 mm, and ACC of 0.91, further validating the robustness of the proposed method across datasets. In terms of Precision (PR) and Sensitivity (SE), the Proposed Method achieved PR = 0.91 and SE = 0.86 on the TG3K dataset, and PR = 0.89 and SE = 0.86 on the TN3K dataset. These results show that our model not only improves segmentation accuracy and boundary delineation (HD95) but also significantly reduces the dependency on pixel-level annotations, providing an effective solution for weakly-supervised thyroid ultrasound segmentation. Our method demonstrates competitive performance with fully-supervised approaches, with reduced annotation time, thereby improving the practicality of deep learning-based segmentation in clinical settings. [Display omitted]
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2025.109669