Name
Abstract | ||
|---|---|---|
Early screening and diagnosis of breast mass are essential for the prevention of breast cancer. There are some reasons to make mass detection be difficult and challenging. First, the resolution of mammography is very large and mass tissues are often subtle. Second, some mass overlap with the normal tissues which own similar texture. In this paper, we propose a novel attention module channel self-attention block (CSABlock), it can make better use of inter-layer features and strengthen the detection capability of the cascade R-CNN model. In order to further improve the detection quality, we also use a new domain-adaptive pre-training strategy. Experiments show that the proposed method achieves an average precision (AP) of 0.822 and average recall (AR) of 0.949, outperforms the state-of-the-art methods. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/BIBM49941.2020.9313473 | BIBM |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| He Xiao | 1 | 0 | 0.34 |
| Qingfeng Wang | 2 | 18 | 7.53 |
| Zhi-qin Liu | 3 | 12 | 4.93 |
| Jun Huang | 4 | 0 | 1.01 |
| Yuwei Zhou | 5 | 0 | 0.34 |
| Ying Zhou | 6 | 0 | 0.34 |
| Weiyun Xu | 7 | 1 | 1.39 |