A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Guoping, Qian, Xiaoxue, Shao, Hua Chieh, Luo, Jax, Lu, Weiguo, Zhang, You
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910714299416576
author Xu, Guoping
Qian, Xiaoxue
Shao, Hua Chieh
Luo, Jax
Lu, Weiguo
Zhang, You
author_facet Xu, Guoping
Qian, Xiaoxue
Shao, Hua Chieh
Luo, Jax
Lu, Weiguo
Zhang, You
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16949
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging
Xu, Guoping
Qian, Xiaoxue
Shao, Hua Chieh
Luo, Jax
Lu, Weiguo
Zhang, You
Computer Vision and Pattern Recognition
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.
title A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.16949