Hierarchical Auto-labeling of Coronary Arteries on CT Coronary Angiography Images

Hierarchical Auto-labeling of Coronary Arteries on CT Coronary Angiography Images

2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

10.1109/EMBC53108.2024.10782317

https://doi.org/10.1109/embc53108.2024.10782317

Jiangyun Li, Zhongkang Lu, Shuang Leng, Xiaohong Wang, Lohendran Baskaran, Min Sen Yew, Mark Chan, Lynette LS Teo, Kee Yuan Ngiam, Hwee Kuan Lee, Liang Zhong, Zhiping Lin, Weimin Huang

Coronary artery disease, CT coronary angiogram, Auto-labeling

17 December 2024

Li, J., Lu, Z., Leng, S., Wang, X., Baskaran, L., Yew, M. S., Chan, M., Teo, L. L., Ngiam, K. Y., Lee, H. K., Zhong, L., Lin, Z., & Huang, W. (2024). Hierarchical Auto-labeling of Coronary Arteries on CT Coronary Angiography Images. 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 1–4. https://doi.org/10.1109/embc53108.2024.10782317

The auto-labeling of coronary artery segments plays an important role in the diagnosis of cardiovascular diseases. Due to the high degree of complexity and diversity in coronary artery structures, it is still a very challenging task after many years of exploration and study. In this paper, we propose a hierarchical scheme based on PointNet++ models and new topological structural features for automatic labeling of coronary artery segments. The inputs are 3D coronary artery centerline points extracted from CTCA images, and the outputs are the correspondent label indexes. The auto-labeling scheme include two stages: first stage is to identify the three main branches, LAD(LM), LCX and RCA. After that, utilizing the topological connectivity relationship with the three main branches, the indexes of sub-branches are identified in the second stage. We evaluated our method on a private clinical dataset. Experimental results show that the proposed method has achieved a satisfactory accuracy for clinical use.

Publisher Copyright

This research / project is supported by the A*STAR, National Research Foundation and EDB - Industry Alignment Fund Pre Positioning
Grant Reference no. : H20c6a0035

© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/21624

2694-0604

Institute for Infocomm Research