A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging
This addresses segmentation challenges in data-scarce medical imaging environments, offering a tool for improved accuracy, though it is incremental as it builds on existing match-based frameworks.
The study tackled the problem of low-quality pseudo labels in semi-supervised medical image segmentation by introducing SAMatch, a framework that uses SAM to refine pseudo labels, achieving state-of-the-art Dice scores of 89.36%, 77.76%, and 80.04% on cardiac MRI, breast ultrasound, and liver datasets with minimal labeled data.
This study introduces SAMatch, a SAM-guided Match-based framework for semi-supervised medical image segmentation, aimed at improving pseudo label quality in data-scarce scenarios. While Match-based frameworks are effective, they struggle with low-quality pseudo labels due to the absence of ground truth. SAM, pre-trained on a large dataset, generalizes well across diverse tasks and assists in generating high-confidence prompts, which are then used to refine pseudo labels via fine-tuned SAM. SAMatch is trained end-to-end, allowing for dynamic interaction between the models. Experiments on the ACDC cardiac MRI, BUSI breast ultrasound, and MRLiver datasets show SAMatch achieving state-of-the-art results, with Dice scores of 89.36%, 77.76%, and 80.04%, respectively, using minimal labeled data. SAMatch effectively addresses challenges in semi-supervised segmentation, offering a powerful tool for segmentation in data-limited environments. Code and data are available at https://github.com/apple1986/SAMatch.