A Teacher-Student Framework with Fourier Augmentation for COVID-19 Infection Segmentation in CT Images

TL;DR

This paper introduces an unsupervised COVID-19 infection segmentation method in CT images using a Fourier-based augmentation and a teacher-student network to learn domain-invariant features, achieving state-of-the-art results without COVID-19 annotations.

Contribution

It proposes a novel unsupervised framework combining Fourier augmentation and a teacher-student network to improve COVID-19 CT segmentation without requiring COVID-19 labeled data.

Findings

Achieves state-of-the-art segmentation performance on COVID-19 CT images.

Effectively reduces domain shift between lung cancer and COVID-19 data.

Demonstrates robustness without COVID-19 annotations during training.

Abstract

Automatic segmentation of infected regions in computed tomography (CT) images is necessary for the initial diagnosis of COVID-19. Deep-learning-based methods have the potential to automate this task but require a large amount of data with pixel-level annotations. Training a deep network with annotated lung cancer CT images, which are easier to obtain, can alleviate this problem to some extent. However, this approach may suffer from a reduction in performance when applied to unseen COVID-19 images during the testing phase due to the domain shift. In this paper, we propose a novel unsupervised method for COVID-19 infection segmentation that aims to learn the domain-invariant features from lung cancer and COVID-19 images to improve the generalization ability of the segmentation network for use with COVID-19 CT images. To overcome the intensity shift, our method first transforms annotated lung cancer data into the style of unlabeled COVID-19 data using an effective augmentation approach via a Fourier transform. Furthermore, to reduce the distribution shift, we design a teacher-student network to learn rotation-invariant features for segmentation. Experiments demonstrate that even without getting access to the annotations of COVID-19 CT during training, the proposed network can achieve a state-of-the-art segmentation performance on COVID-19 images.