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

by   Chenyu You, et al.

Medical data often exhibits long-tail distributions with heavy class imbalance, which naturally leads to difficulty in classifying the minority classes (i.e., boundary regions or rare objects). Recent work has significantly improved semi-supervised medical image segmentation in long-tailed scenarios by equipping them with unsupervised contrastive criteria. However, it remains unclear how well they will perform in the labeled portion of data where class distribution is also highly imbalanced. In this work, we present ACTION++, an improved contrastive learning framework with adaptive anatomical contrast for semi-supervised medical segmentation. Specifically, we propose an adaptive supervised contrastive loss, where we first compute the optimal locations of class centers uniformly distributed on the embedding space (i.e., off-line), and then perform online contrastive matching training by encouraging different class features to adaptively match these distinct and uniformly distributed class centers. Moreover, we argue that blindly adopting a constant temperature τ in the contrastive loss on long-tailed medical data is not optimal, and propose to use a dynamic τ via a simple cosine schedule to yield better separation between majority and minority classes. Empirically, we evaluate ACTION++ on ACDC and LA benchmarks and show that it achieves state-of-the-art across two semi-supervised settings. Theoretically, we analyze the performance of adaptive anatomical contrast and confirm its superiority in label efficiency.


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

Contrastive learning has shown great promise over annotation scarcity pr...

Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation

Contrastive Learning (CL) is a recent representation learning approach, ...

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

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

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

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

Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation

Semi-supervised segmentation remains challenging in medical imaging sinc...

ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classification

Medical image classification has been widely adopted in medical image an...

Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data

Most approaches for self-supervised learning (SSL) are optimised on cura...

Please sign up or login with your details

Forgot password? Click here to reset