Multiscale Switch for Semi-Supervised and Contrastive Learning in Medical Ultrasound Image Segmentation

2026-03-19

AI Summary

Medical ultrasound image segmentation is hindered by scarce annotations, speckle noise, and low-contrast boundaries. To address these challenges, this work proposes Switch, a teacher–student framework that integrates Multi-scale Switching (MSS) and Frequency-domain Amplitude Switching (FDS), introducing frequency-domain contrastive learning to ultrasound segmentation for the first time. MSS ensures uniform spatial coverage, while FDS enhances feature robustness, enabling effective exploitation of limited labeled data alongside abundant unlabeled data. Evaluated on six ultrasound datasets, the method achieves Dice scores of 80.04%–85.52% using only 5% labeled data—surpassing fully supervised baselines—while maintaining a compact model size of just 1.8 million parameters.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Medical ultrasound image segmentation faces significant challenges due to limited labeled data and characteristic imaging artifacts including speckle noise and low-contrast boundaries. While semi-supervised learning (SSL) approaches have emerged to address data scarcity, existing methods suffer from suboptimal unlabeled data utilization and lack robust feature representation mechanisms. In this paper, we propose Switch, a novel SSL framework with two key innovations: (1) Multiscale Switch (MSS) strategy that employs hierarchical patch mixing to achieve uniform spatial coverage; (2) Frequency Domain Switch (FDS) with contrastive learning that performs amplitude switching in Fourier space for robust feature representations. Our framework integrates these components within a teacher-student architecture to effectively leverage both labeled and unlabeled data. Comprehensive evaluation across six diverse ultrasound datasets (lymph nodes, breast lesions, thyroid nodules, and prostate) demonstrates consistent superiority over state-of-the-art methods. At 5\% labeling ratio, Switch achieves remarkable improvements: 80.04\% Dice on LN-INT, 85.52\% Dice on DDTI, and 83.48\% Dice on Prostate datasets, with our semi-supervised approach even exceeding fully supervised baselines. The method maintains parameter efficiency (1.8M parameters) while delivering superior performance, validating its effectiveness for resource-constrained medical imaging applications. The source code is publicly available at https://github.com/jinggqu/Switch

Problem

• medical ultrasound image segmentation
• limited labeled data
• speckle noise
• low-contrast boundaries
• semi-supervised learning

Innovation

• Multiscale Switch
• Frequency Domain Switch
• Semi-Supervised Learning
• Contrastive Learning
• Ultrasound Image Segmentation