TY - JOUR
T1 - A teacher–student framework with Fourier Transform augmentation for COVID-19 infection segmentation in CT images
AU - Chen, Han
AU - Jiang, Yifan
AU - Ko, Hanseok
AU - Loew, Murray
N1 - Funding Information:
This research is supported by the Government-Wide R&D Fund Project for Infectious Disease Research (GFID) , Republic of Korea (grant number: HG19C0682) .
Publisher Copyright:
© 2022 Elsevier Ltd
PY - 2023/1
Y1 - 2023/1
N2 - 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, caused by the difference in the image intensity and object region distribution between the training set and test set. In this paper, we proposed 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. First, to address the intensity difference, we proposed a novel data augmentation module based on Fourier Transform, which transfers the annotated lung cancer data into the style of COVID-19 image. Secondly, to reduce the distribution difference, we designed a teacher–student network to learn rotation-invariant features for segmentation. The experiments demonstrated that even without getting access to the annotations of the COVID-19 CT images during the training phase, the proposed network can achieve a state-of-the-art segmentation performance on COVID-19 infection.
AB - 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, caused by the difference in the image intensity and object region distribution between the training set and test set. In this paper, we proposed 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. First, to address the intensity difference, we proposed a novel data augmentation module based on Fourier Transform, which transfers the annotated lung cancer data into the style of COVID-19 image. Secondly, to reduce the distribution difference, we designed a teacher–student network to learn rotation-invariant features for segmentation. The experiments demonstrated that even without getting access to the annotations of the COVID-19 CT images during the training phase, the proposed network can achieve a state-of-the-art segmentation performance on COVID-19 infection.
KW - COVID-19
KW - Computed tomography
KW - Fourier Transform
KW - Infection segmentation
KW - Teacher–student network
UR - http://www.scopus.com/inward/record.url?scp=85139030607&partnerID=8YFLogxK
U2 - 10.1016/j.bspc.2022.104250
DO - 10.1016/j.bspc.2022.104250
M3 - Article
AN - SCOPUS:85139030607
SN - 1746-8094
VL - 79
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
M1 - 104250
ER -