GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labels
Open Access
- 26 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 463-471
Abstract
Since annotating medical images for segmentation tasks commonly incurs expensive costs, it is highly desirable to design an annotation-efficient method to alleviate the annotation burden. Recently, contrastive learning has exhibited a great potential in learning robust representations to boost downstream tasks with limited labels. In medical imaging scenarios, ready-made meta labels (i.e., specific attribute information of medical images) inherently reveal semantic relationships among images, which have been used to define positive pairs in previous work. However, the multi-perspective semantics revealed by various meta labels are usually incompatible and can incur intractable "semantic contradiction" when combining different meta labels. In this paper, we tackle the issue of "semantic contradiction" in a gradient-guided manner using our proposed Gradient Mitigator method, which systematically unifies multi-perspective meta labels to enable a pre-trained model to attain a better high-level semantic recognition ability. Moreover, we emphasize that the fine-grained discrimination ability is vital for segmentation-oriented pre-training, and develop a novel method called Gradient Filter to dynamically screen pixel pairs with the most discriminating power based on the magnitude of gradients. Comprehensive experiments on four medical image segmentation datasets verify that our new method GCL: (1) learns informative image representations and considerably boosts segmentation performance with limited labels, and (2) shows promising generalizability on out-of-distribution datasets.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62176231,92259202)
This publication has 16 references indexed in Scilit:
- Positional Contrastive Learning for Volumetric Medical Image Segmentation2021
- Electrocardio Panorama: Synthesizing New ECG views with Self-supervision2021
- Dense Contrastive Learning for Self-Supervised Visual Pre-Training2021
- Self-Supervised Learning of Pretext-Invariant Representations2020
- Deep Semi-supervised Segmentation with Weight-Averaged Consistency Targets2018
- Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images2017
- Context Encoders: Feature Learning by Inpainting2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Challenges and Methodologies of Fully Automatic Whole Heart Segmentation: A ReviewJournal of Healthcare Engineering, 2013
- Stochastic Gradient Descent Tricks2012