Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer

TL;DR

This paper introduces a novel semi-supervised medical image segmentation framework that leverages cross teaching between CNN and Transformer networks, outperforming existing methods on benchmark datasets.

Contribution

It is the first to combine CNN and Transformer for semi-supervised medical image segmentation, simplifying co-training with effective cross teaching.

Findings

Outperforms eight existing semi-supervised methods

Effective cross teaching between CNN and Transformer

Promising results on a public benchmark

Abstract

Recently, deep learning with Convolutional Neural Networks (CNNs) and Transformers has shown encouraging results in fully supervised medical image segmentation. However, it is still challenging for them to achieve good performance with limited annotations for training. In this work, we present a very simple yet efficient framework for semi-supervised medical image segmentation by introducing the cross teaching between CNN and Transformer. Specifically, we simplify the classical deep co-training from consistency regularization to cross teaching, where the prediction of a network is used as the pseudo label to supervise the other network directly end-to-end. Considering the difference in learning paradigm between CNN and Transformer, we introduce the Cross Teaching between CNN and Transformer rather than just using CNNs. Experiments on a public benchmark show that our method outperforms eight existing semi-supervised learning methods just with a simpler framework. Notably, this work may be the first attempt to combine CNN and transformer for semi-supervised medical image segmentation and achieve promising results on a public benchmark. The code will be released at: https://github.com/HiLab-git/SSL4MIS.