Weakly Supervised Segmentation Framework for Thyroid Nodule Based on High-confidence Labels and High-rationality Losses

TL;DR

This paper proposes a novel weakly supervised segmentation framework for thyroid nodules in ultrasound images, utilizing high-confidence labels and rationality losses to improve accuracy and robustness over existing methods.

Contribution

The framework introduces high-confidence pseudo-labels and multi-level discriminative losses, effectively addressing label noise and shape diversity in ultrasound nodule segmentation.

Findings

Achieves state-of-the-art performance on TN3K and DDTI datasets.

Effectively reduces label noise and improves nodule boundary accuracy.

Demonstrates robustness to diverse nodule shapes and complex structures.

Abstract

Weakly supervised segmentation methods can delineate thyroid nodules in ultrasound images efficiently using training data with coarse labels, but suffer from: 1) low-confidence pseudo-labels that follow topological priors, introducing significant label noise, and 2) low-rationality loss functions that rigidly compare segmentation with labels, ignoring discriminative information for nodules with diverse and complex shapes. To solve these issues, we clarify the objective and references for weakly supervised ultrasound image segmentation, presenting a framework with high-confidence pseudo-labels to represent topological and anatomical information and high-rationality losses to capture multi-level discriminative features. Specifically, we fuse geometric transformations of four-point annotations and MedSAM model results prompted by specific annotations to generate high-confidence box, foreground, and background labels. Our high-rationality learning strategy includes: 1) Alignment loss measuring spatial consistency between segmentation and box label, and topological continuity within the foreground label, guiding the network to perceive nodule location; 2) Contrastive loss pulling features from labeled foreground regions while pushing features from labeled foreground and background regions, guiding the network to learn nodule and background feature distribution; 3) Prototype correlation loss measuring consistency between correlation maps derived by comparing features with foreground and background prototypes, refining uncertain regions to accurate nodule edges. Experimental results show that our method achieves state-of-the-art performance on the TN3K and DDTI datasets. The code is available at https://github.com/bluehenglee/MLI-MSC.