Name
Title | ||
|---|---|---|
Dense biased networks with deep priori anatomy and hard region adaptation: Semi-supervised learning for fine renal artery segmentation. |
Abstract | ||
|---|---|---|
•A novel 3D semi-supervised segmentation framework for fine renal artery segmentation task for the first time.•A dense biased connection method and a dense biased network (DenseBiasNet) are proposed for renal artery’s large intra-scale changes problem and training process optimization.•A semi-supervised learning strategy (DPA) which embeds deep priori anatomy features in network to handle the large inter-anatomy variation problem and the limitation of labeled dataset.•A hard region adaptation (HRA) loss function for category imbalanced problem.•Proof of the effectiveness of the proposed framework and analyze the role of different parts. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.media.2020.101722 | Medical Image Analysis |
Keywords | DocType | Volume |
Renal artery segmentation,Semi-supervised learning,Dense biased network,Dense biased connection,Deep priori anatomy,Hard region adaptation loss function,3D fine segmentation,CT angiography image | Journal | 63 |
ISSN | Citations | PageRank |
1361-8415 | 1 | 0.35 |
References | Authors | |
0 | 14 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yuting He | 1 | 5 | 4.45 |
| Guanyu Yang | 2 | 27 | 13.48 |
| Jian Yang | 3 | 283 | 48.62 |
| Yang Chen | 4 | 5 | 5.14 |
| Youyong Kong | 5 | 96 | 15.23 |
| Jiasong Wu | 6 | 49 | 9.33 |
| Lijun Tang | 7 | 3 | 2.09 |
| Xiaomei Zhu | 8 | 109 | 12.21 |
| Jean-Louis Dillenseger | 9 | 5 | 4.79 |
| Pengfei Shao | 10 | 4 | 1.40 |
| Shaobo Zhang | 11 | 4 | 1.40 |
| Huazhong Shu | 12 | 940 | 90.05 |
| J L Coatrieux | 13 | 273 | 51.89 |
| Shuo Li | 14 | 887 | 72.47 |