Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation

by   Chenyu You, et al.

Contrastive learning has shown great promise over annotation scarcity problems in the context of medical image segmentation. Existing approaches typically assume a balanced class distribution for both labeled and unlabeled medical images. However, medical image data in reality is commonly imbalanced (i.e., multi-class label imbalance), which naturally yields blurry contours and usually incorrectly labels rare objects. Moreover, it remains unclear whether all negative samples are equally negative. In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation. Specifically, we first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs. We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data. Second, we raise a more important question: Can we really handle imbalanced samples to yield better performance? Hence, the key innovation in ACTION is to learn global semantic relationship across the entire dataset and local anatomical features among the neighbouring pixels with minimal additional memory footprint. During the training, we introduce anatomical contrast by actively sampling a sparse set of hard negative pixels, which can generate smoother segmentation boundaries and more accurate predictions. Extensive experiments across two benchmark datasets and different unlabeled settings show that ACTION performs comparable or better than the current state-of-the-art supervised and semi-supervised methods. Our code and models will be publicly available.


Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective

For medical image segmentation, contrastive learning is the dominant pra...

ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast

Medical data often exhibits long-tail distributions with heavy class imb...

Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels

Recent studies on contrastive learning have achieved remarkable performa...

Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation

Deep learning has demonstrated significant improvements in medical image...

DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation

The volume-wise labeling of 3D medical images is expertise-demanded and ...

SSHNN: Semi-Supervised Hybrid NAS Network for Echocardiographic Image Segmentation

Accurate medical image segmentation especially for echocardiographic ima...

Min-Max Similarity: A Contrastive Learning Based Semi-Supervised Learning Network for Surgical Tools Segmentation

Segmentation of images is a popular topic in medical AI. This is mainly ...

Please sign up or login with your details

Forgot password? Click here to reset