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.