Automatic coronary artery labeling based on point cloud and connectivity features
Automatic coronary artery labeling is of great significance for automatic generation of cardiovascular disease diagnosis reports. Traditional methods include model-based and learning-based methods, but due to the complex and changeable vascular structure, automatic coronary artery segment labeling i...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
Nanyang Technological University
2023
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/167795 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Automatic coronary artery labeling is of great significance for automatic generation of cardiovascular disease diagnosis reports. Traditional methods include model-based and learning-based methods, but due to the complex and changeable vascular structure, automatic coronary artery segment labeling is still very challenging. In this paper, we adapt an innovative connectivity feature in pointnet++ model architecture for automatic coronary artery segment labeling. The inputs are 3D coronary artery centerline points extracted from CTCA images and their connectivity features, and the outputs are the index of coronary artery segments. We evaluated our method on a real-clinical dataset. Experimental results show that the proposed method has high accuracy and short interference time. |
|---|