Title | ||
---|---|---|
COVID-19 lung infection segmentation with a novel two-stage cross-domain transfer learning framework |
Abstract | ||
---|---|---|
•We propose a novel two-stage transfer learning framework for segmenting COVID-19 lung infections from CT images. Our framework learns valuable knowledge from both natural images and CT images with pulmonary nodules, allowing more effective network training for improved performance.•We propose an effective infection segmentation network, called nCoVSegNet, which takes advantage of attention-aware feature fusion and large reception fields for accurate segmentation of lung infections.•Extensive experiments on two COVID-19 CT datasets demonstrate that our framework is able to segment lung infections accurately and outperforms state-of-the-art methods remarkably. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.media.2021.102205 | Medical Image Analysis |
Keywords | DocType | Volume |
COVID-19,Lung infection segmentation,Transfer learning,Computed tomography | Journal | 74 |
ISSN | Citations | PageRank |
1361-8415 | 2 | 0.53 |
References | Authors | |
21 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiannan Liu | 1 | 2 | 0.53 |
Bo Dong | 2 | 243 | 29.31 |
Shuai Wang | 3 | 2 | 0.53 |
Hui Cui | 4 | 7 | 8.76 |
Deng-Ping Fan | 5 | 51 | 1.98 |
Jiquan Ma | 6 | 2 | 2.22 |
Geng Chen | 7 | 73 | 16.95 |