Contrastive learning of global and local features for medical image segmentation with limited annotations

by   Krishna Chaitanya, et al.

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to pre-train a neural network with unlabeled data, followed by fine-tuning for a downstream task with limited annotations. Contrastive learning, a particular variant of SSL, is a powerful technique for learning image-level representations. In this work, we propose strategies for extending the contrastive learning framework for segmentation of volumetric medical images in the semi-supervised setting with limited annotations, by leveraging domain-specific and problem-specific cues. Specifically, we propose (1) novel contrasting strategies that leverage structural similarity across volumetric medical images (domain-specific cue) and (2) a local version of the contrastive loss to learn distinctive representations of local regions that are useful for per-pixel segmentation (problem-specific cue). We carry out an extensive evaluation on three Magnetic Resonance Imaging (MRI) datasets. In the limited annotation setting, the proposed method yields substantial improvements compared to other self-supervision and semi-supervised learning techniques. When combined with a simple data augmentation technique, the proposed method reaches within 8 for training, corresponding to only 4 train the benchmark.


page 7

page 8

page 14


FBA-Net: Foreground and Background Aware Contrastive Learning for Semi-Supervised Atrium Segmentation

Medical image segmentation of gadolinium enhancement magnetic resonance ...

Positional Contrastive Learning for Volumetric Medical Image Segmentation

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

MixCL: Pixel label matters to contrastive learning

Contrastive learning and self-supervised techniques have gained prevalen...

Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation

Deep learning highly relies on the quantity of annotated data. However, ...

Attention-Guided Supervised Contrastive Learning for Semantic Segmentation

Contrastive learning has shown superior performance in embedding global ...

IDEAL: Improved DEnse locAL Contrastive Learning for Semi-Supervised Medical Image Segmentation

Due to the scarcity of labeled data, Contrastive Self-Supervised Learnin...

Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentation

The success of deep learning methods in medical image segmentation tasks...

Please sign up or login with your details

Forgot password? Click here to reset