CCAT-NET: A Novel Transformer Based Semi-supervised Framework for Covid-19 Lung Lesion Segmentation

TL;DR

This paper introduces CCAT-NET, a hybrid CNN-Transformer model with a semi-supervised learning framework for improved COVID-19 lung lesion segmentation from CT images, addressing data scarcity and outperforming existing methods.

Contribution

It presents a novel CNN-Transformer architecture combined with a semi-supervised framework specifically designed for COVID-19 lesion segmentation.

Findings

Outperforms existing networks in segmentation accuracy.

Semi-supervised framework improves performance by 3.0% Dice and 8.2% sensitivity.

Effective in scenarios with limited labeled data.

Abstract

The spread of the novel coronavirus disease 2019 (COVID-19) has claimed millions of lives. Automatic segmentation of lesions from CT images can assist doctors with screening, treatment, and monitoring. However, accurate segmentation of lesions from CT images can be very challenging due to data and model limitations. Recently, Transformer-based networks have attracted a lot of attention in the area of computer vision, as Transformer outperforms CNN at a bunch of tasks. In this work, we propose a novel network structure that combines CNN and Transformer for the segmentation of COVID-19 lesions. We further propose an efficient semi-supervised learning framework to address the shortage of labeled data. Extensive experiments showed that our proposed network outperforms most existing networks and the semi-supervised learning framework can outperform the base network by 3.0% and 8.2% in terms of Dice coefficient and sensitivity.