Related Experiment Video
Updated: May 30, 2025
Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
Published on: September 22, 2023
LASF: a local adaptive segmentation framework for coronary angiogram segments
Hao Ren1,2,3, Dongxiao Li4, Fengshi Jing1,5
1Faculty of Data Science, City University of Macau, Taipa, 999078 Macao Special Administrative Region China.
Insights
A new Local Adaptive Segmentation Framework (LASF) improves coronary artery disease (CAD) diagnosis by enhancing medical imaging segmentation. This AI tool offers more accurate vessel identification in coronary angiograms for better patient outcomes.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Cardiovascular Disease Research
Background:
- Coronary artery disease (CAD) is a leading global cause of mortality.
- Current coronary angiogram segmentation methods face challenges with vessel discontinuity and accuracy.
- Accurate segmentation is crucial for effective CAD diagnosis and treatment planning.
Purpose of the Study:
- To develop an advanced segmentation framework for coronary angiograms.
- To improve the precision and continuity of vascular segmentation in medical images.
- To enhance the diagnostic capabilities for coronary artery disease.
Main Methods:
- Developed the Local Adaptive Segmentation Framework (LASF) by enhancing the YOLOv8 architecture.
- Integrated dilation and erosion algorithms into the YOLOv8 model for improved segmentation.
- Enriched the ARCADE dataset with detailed annotations of proximal and distal vascular segments.
- Performed comparative analyses against established models like UNet and DeepLabV3Plus.
Main Results:
- LASF demonstrated superior performance compared to UNet and DeepLabV3Plus.
- Achieved higher precision, recall, and F1-scores in vascular segmentation tasks.
- The enhanced ARCADE dataset improved the robustness of segmentation models.
- LASF effectively addressed issues of vessel discontinuity and segmentation inaccuracies.
Conclusions:
- LASF offers a significant advancement in segmenting vascular images from coronary angiograms.
- The framework provides more reliable and accurate segmentation critical for clinical applications.
- LASF has the potential to improve the clinical management of CAD, enhancing diagnostic accuracy and patient outcomes.
Abstract:
Coronary artery disease (CAD) remains the leading cause of death globally, highlighting the critical need for accurate diagnostic tools in medical imaging. Traditional segmentation methods for coronary angiograms often struggle with vessel discontinuity and inaccuracies, impeding effective diagnosis and treatment planning. To address these challenges, we developed the Local Adaptive Segmentation Framework (LASF), enhancing the YOLOv8 architecture with dilation and erosion algorithms to improve the continuity and precision of vascular image segmentation. We further enriched the ARCADE dataset by meticulously annotating both proximal and distal vascular segments, thus broadening the dataset's applicability for training robust segmentation models. Our comparative analyses reveal that LASF outperforms well-known models such as UNet and DeepLabV3Plus, demonstrating superior metrics in precision, recall, and F1-score across various testing scenarios. These enhancements ensure more reliable and accurate segmentation, critical for clinical applications. LASF represents a significant advancement in the segmentation of vascular images within coronary angiograms. By effectively addressing the common issues of vessel discontinuity and segmentation accuracy, LASF stands to improve the clinical management of CAD, offering a promising tool for enhancing diagnostic accuracy and patient outcomes in medical settings.
