Mask SAM 3D for coronary artery and plaque segmentation in CCTA images
RenZhe Tu1,2, CongYu Tian1,2, LinYuan Wang3
1Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Insights
Researchers developed Mask SAM 3D for joint segmentation of coronary arteries and atherosclerotic plaques. This novel framework improves accuracy for both artery and plaque segmentation in cardiovascular imaging.
Area of Science:
- Cardiovascular Imaging and Diagnostics
- Medical Image Analysis
- Artificial Intelligence in Medicine
Background:
- Coronary artery disease (CAD) poses a significant global health burden, particularly in obstructive cases.
- Accurate segmentation of coronary arteries and atherosclerotic plaques is crucial for effective patient management and treatment planning.
- Existing research lacks a unified framework for the simultaneous segmentation of both coronary arteries and plaques.
Purpose of the Study:
- To introduce a novel framework, Mask SAM 3D, for the joint segmentation of coronary arteries and atherosclerotic plaques.
- To address the limitations of previous studies by providing a unified approach to segmenting these critical cardiovascular components.
- To develop an innovative method that enhances the accuracy of both artery and plaque segmentation within a single model.
Main Methods:
- Development of the PCCTA120 dataset, comprising 120 annotated CCTA volumes for coronary arteries and atherosclerotic plaques.
- Implementation of Mask SAM 3D, a framework utilizing nnUNet for precise coronary artery mask generation.
- Introduction of a plaque-aware adapter and a prototype-guided prediction module to refine plaque localization and enhance segmentation accuracy.
Main Results:
- The Mask SAM 3D framework achieved a Dice similarity coefficient of 84.5% for artery segmentation.
- The method obtained a Dice similarity coefficient of 55.2% for plaque segmentation.
- Performance metrics demonstrated that the proposed method outperforms current state-of-the-art techniques on the PCCTA120 dataset.
Conclusions:
- The public release of the PCCTA120 dataset aims to foster advancements in cardiovascular research.
- The Mask SAM 3D framework successfully improves the accuracy of both coronary artery and atherosclerotic plaque segmentation.
- The study provides a valuable tool for the cardiovascular research community, with source code and dataset to be made publicly available.
Purpose:
Coronary artery disease is a major global cause of morbidity and mortality, especially in obstructive CAD patients. Precise segmentation of coronary arteries and atherosclerotic plaques is essential for effective treatment. However, no previous study has addressed the joint segmentation of these two within a unified framework, which motivates our work.
Methods:
We built a dataset, namely PCCTA120, consisting of 120 CCTA volumes, each annotated with manually delineated masks for coronary arteries and atherosclerotic plaques. We then present Mask SAM 3D, an innovative framework designed for joint segmentation of these two components. In the context of plaque localization within coronary arteries, accurately identifying plaques is a complex task due to the intricate nature of coronary artery and the subtle differences in plaque appearance. To simplify this challenge, we recognized the need for a reliable prior of well-defined artery skeleton and proposed to first generate a precise coronary artery mask with nnUNet. Subsequently, a novel plaque-aware adapter is developed to intensify semantic interactions and refines the accuracy of plaque localization by capitalizing on the prior information embedded within the generated coronary artery mask. Meanwhile, to enhance the model's discriminative ability for accurate joint segmentation, a prototype-guided prediction module that dynamically clusters embedded features into class-specific prototypes is introduced.
Results:
Experiments conducted on our self-built dataset show that our method achieves Dice similarity coefficients of 84.5% for artery segmentation and 55.2% for plaque segmentation, outperforming current state-of-the-art methods.
Conclusion:
First, we release a new coronary arteries and atherosclerotic plaques segmentation dataset, PCCTA120, to advance the cardiovascular research community. Meanwhile, our framework, Mask SAM 3D, cannot only improve the accuracy of artery segmentation but also enhances that of plaque segmentation. Source code and dataset will be made publicly available.
More Related Videos
06:57Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
Published on: September 22, 2023
09:57Development and Evaluation of 3D-Printed Cardiovascular Phantoms for Interventional Planning and Training
Published on: January 18, 2021
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:28Imaging Studies for Cardiovascular System V: CT