Dual Multiscale Mean Teacher Network for Semi-Supervised Infection Segmentation in Chest CT Volume for COVID-19

Page view(s)
58
Checked on Oct 03, 2024
Dual Multiscale Mean Teacher Network for Semi-Supervised Infection Segmentation in Chest CT Volume for COVID-19
Title:
Dual Multiscale Mean Teacher Network for Semi-Supervised Infection Segmentation in Chest CT Volume for COVID-19
Journal Title:
IEEE Transactions on Cybernetics
Publication Date:
14 December 2022
Citation:
Wang, L., Wang, J., Zhu, L., Fu, H., Li, P., Cheng, G., Feng, Z., Li, S., & Heng, P.-A. (2022). Dual Multiscale Mean Teacher Network for Semi-Supervised Infection Segmentation in Chest CT Volume for COVID-19. IEEE Transactions on Cybernetics, 1–13. https://doi.org/10.1109/tcyb.2022.3223528
Abstract:
Automated detecting lung infections from computed tomography (CT) data plays an important role for combating COVID-19. However, there are still some challenges for developing AI system. 1) Most current COVID-19 infection segmentation methods mainly relied on 2D CT images, which lack 3D sequential constraint. 2) Existing 3D CT segmentation methods focus on single-scale representations, which do not achieve the multiple level receptive field sizes on 3D volume. 3) The emergent breaking out of COVID-19 makes it hard to annotate sufficient CT volumes for training deep model. To address these issues, we first build a multiple dimensional-attention convolutional neural network (MDA-CNN) to aggregate multi-scale information along different dimension of input feature maps and impose supervision on multiple predictions from different CNN layers. Second, we assign this MDA-CNN as a basic network into a novel dual multi-scale mean teacher network (DM2T-Net) for semi-supervised COVID-19 lung infection segmentation on CT volumes by leveraging unlabeled data and exploring the multi-scale information. Our DM2T-Net encourages multiple predictions at different CNN layers from the student and teacher networks to be consistent for computing a multi-scale consistency loss on unlabeled data, which is then added to the supervised loss on the labeled data from multiple predictions of MDA-CNN. Third, we collect two COVID-19 segmentation datasets to evaluate our method. The experimental results show that our network consistently outperforms the compared state-of-the-art methods.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the AI Singapore - Tech Challenge Funding
Grant Reference no. : AISG2-TC-2021-003

This work was supported in part by the National Key Research and Development Program of China under Grant 2019YFE0113900; in part by the National Natural Science Foundation of China under Project 61902275.
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2168-2275
2168-2267
Files uploaded:

File Size Format Action
dual-multiscale-mean-teacher-network-for-semi-supervised-infection-segmentation-in-chest-ct-volume-for-covid-19.pdf 1.81 MB PDF Request a copy