| Paper ID | BIO-3.5 |
| Paper Title |
Graph-Based Pyramid Global Context Reasoning with A Saliency-Aware Projection for COVID-19 Lung Infections Segmentation |
| Authors |
Huimin Huang, Ming Cai, Lanfen Lin, Zhejiang University, China; Jing Zheng, Xiongwei Mao, Xiaohan Qian, Zhiyi Peng, Jianying Zhou, The First Affiliated Hospital, China; Yutaro Iwamoto, Xian-Hua Han, Yen-Wei Chen, Ritsumeikan University, Japan; Ruofeng Tong, Zhejiang University, China |
| Session | BIO-3: Machine Learning for COVID-19 diagnosis |
| Location | Gather.Town |
| Session Time: | Tuesday, 08 June, 13:00 - 13:45 |
| Presentation Time: | Tuesday, 08 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Biomedical Imaging and Signal Processing: [BIO-MIA] Medical image analysis |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Coronavirus Disease 2019 (COVID-19) has rapidly spread in 2020, emerging a mass of studies for lung infection segmentation from CT images. Though many methods have been proposed for this issue, it is a challenging task because of infections of various size appearing in different lobe zones. To tackle these issues, we propose a Graph-based Pyramid Global Context Reasoning (Graph-PGCR) module, which is capable of modeling long-range dependencies among disjoint infections as well as adapt size variation. We first incorporate graph convolution to exploit long-term contextual information from multiple lobe zones. Different from previous average pooling or maximum object probability, we proposed a saliency-aware projection mechanism to pick up infection-related pixels as a set of graph nodes. After graph reasoning, the relation-aware features are reversed back to the coordinate space for the down-stream tasks. We further construct multiple graphs with different sampling rates to handle the size variation problem. To this end, distinct multi-scale long-range contextual patterns can be captured. Our Graph-PGCR module is plug-and-play, which can be integrated into any architecture to improve its performance. Experiments demonstrated that the proposed method consistently boost the performance of state-of-the-art backbone architectures on both of public and our private COVID-19 datasets. |
