When a stress-induced perfusion defect exists on PET, revascularization improves sMBF in that region. When there is no such defect, sMBF shows no net change, whether or not intervention is performed in that area. PET stress may be useful for identifying areas of myocardium that could benefit from revascularization, and also areas in which intervention is unlikely to yield improvement in myocardial blood flow.

Coronary artery disease (CAD) is the leading cause of death worldwide, constituting more than one-fourth of global mortalities every year. Accurate semantic segmentation of each artery in fluoroscopy angiograms is important for assessment of the stenosis and CAD diagnosis and treatment. However, due to the morphological similarity among different types of arteries, it is hard for deep-learning-based models to generate semantic segmentation with an end-toend approach. In this paper, we propose a multi-step semantic segmentation algorithm based on the analysis of graphs extracted from fluoroscopy angiograms. The proposed algorithm firstly extracts the entire arterial binary mask (binary vascular tree) by Feature Pyramid U-Net++. Then we extract the centerline of the binary vascular tree and separate it into different vessel segments. Finally, by extracting the underlying arterial topology, position and pixel features, we construct a powerful coronary artery classifier based on random forest. Each vessel segment is classified into left coronary artery (LCA), left anterior descending (LAD) and other types of arterial segments. We tested the proposed method on a dataset with 69 LAO and 103 RAO fluoroscopic angiograms and achieved classification accuracies of 66.4% and 61.49% respectively. The experimental results show the effectiveness of the proposed algorithm, which can be used to analyze the individual arteries in fluoroscopy angiograms.

No abstract

No abstract