Self-supervised learning based transformer and convolution hybrid network for one-shot organ segmentation

Abstract

Few-shot medical segmentation aims at segmenting the desired regions from the input medical imaging data with only a pre-annotated example as the reference. By using the minimal annotation data to facilitate the segmentation, the few-shot manner receives great attention in the medial image analysis community due to its weak requirement on human annotation. For one-shot segmentation methods, one core issue is to learn a feature embedding space where the features of the desired segmentation regions on the unlabeled image and the references are high correlation. Previous works rely on the similarity between image features as a constraint to establish such embedding space, ignoring the correlation between samples mined from image features. To address this issue, we propose a novel transformer and convolution hybrid network for building the global correlation between the reference sample (support) and the desired segmentation sample (query). The convolution network is first to extract the local features of the support and query, then, the transformer further extracts the global features from the local feature space. To build the global correction between the support and query, we proposed a semantic dependency relationship embedding which introduces the channel-wise and spatial-wise co-information of them to the transformer. We employ superpixel-based self-supervised learning to train the proposed network to solve the problem of insufficient training samples in the field of medical image segmentation. Comprehensive experiments on two benchmarks demonstrate the superior capacity of the proposed approach when compared to the current alternatives and baseline models.