Enhancing Coronary Artery Calcium Scoring via Multi-Organ Segmentation on Non-Contrast Cardiac Computed Tomography

2025-01-20

AI Summary

To address the low accuracy and poor interpretability of coronary artery calcium (CAC) scoring in non-contrast cardiac CT, this paper proposes an anatomy-aware paradigm that abandons conventional lesion-detection strategies. Instead, it leverages multi-organ semantic segmentation as a structural prior for CAC scoring, jointly modeling anatomical context—including the heart and adjacent organs—via a deep learning network. Anatomically constrained post-processing and precise calcification localization algorithms are further integrated. This is the first method to simultaneously optimize quantitative CAC measurement and structural interpretability. Evaluated on an open-source, multi-vendor dataset, it achieves inter-radiologist agreement levels—significantly outperforming existing state-of-the-art methods—while effectively distinguishing coronary from aortic calcifications and suppressing noise-induced false positives.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Despite coronary artery calcium scoring being considered a largely solved problem within the realm of medical artificial intelligence, this paper argues that significant improvements can still be made. By shifting the focus from pathology detection to a deeper understanding of anatomy, the novel algorithm proposed in the paper both achieves high accuracy in coronary artery calcium scoring and offers enhanced interpretability of the results. This approach not only aids in the precise quantification of calcifications in coronary arteries, but also provides valuable insights into the underlying anatomical structures. Through this anatomically-informed methodology, the paper shows how a nuanced understanding of the heart's anatomy can lead to more accurate and interpretable results in the field of cardiovascular health. We demonstrate the superior accuracy of the proposed method by evaluating it on an open-source multi-vendor dataset, where we obtain results at the inter-observer level, surpassing the current state of the art. Finally, the qualitative analyses show the practical value of the algorithm in such tasks as labeling coronary artery calcifications, identifying aortic calcifications, and filtering out false positive detections due to noise.

Problem

• Coronary Artery Calcification
• Non-Contrast Cardiac CT
• Algorithm Enhancement

Innovation

• Cardiac Structure Understanding
• Calcification Detection Accuracy
• Interpretable Analysis