GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labels

by   Yixuan Wu, et al.

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.


page 1

page 5


Multi-level Asymmetric Contrastive Learning for Medical Image Segmentation Pre-training

Contrastive learning, which is a powerful technique for learning image-l...

Positional Contrastive Learning for Volumetric Medical Image Segmentation

The success of deep learning heavily depends on the availability of larg...

Modeling Human Preference and Stochastic Error for Medical Image Segmentation with Multiple Annotators

Manual annotation of medical images is highly subjective, leading to ine...

Unified Medical Image-Text-Label Contrastive Learning With Continuous Prompt

Contrastive language-image Pre-training (CLIP) [13] can leverage large d...

Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels

Contrastive Learning has shown impressive results on natural and medical...

Weakly Supervised Medical Image Segmentation

In this paper, we propose a novel approach for few-shot semantic segment...

Robust and Efficient Segmentation of Cross-domain Medical Images

Efficient medical image segmentation aims to provide accurate pixel-wise...

Please sign up or login with your details

Forgot password? Click here to reset