Two New Stenoses Detection Methods of Coronary Angiograms

by   Yaofang Liu, et al.

Coronary angiography is the "gold standard" for the diagnosis of coronary heart disease. At present, the methods for detecting coronary artery stenoses and evaluating the degree of it in coronary angiograms are either subjective or not efficient enough. Two vascular stenoses detection methods in coronary angiograms are proposed to assist the diagnosis. The first one is an automatic method, which can automatically segment the entire coronary vessels and mark the stenoses. The second one is an interactive method. With this method, the user only needs to give a start point and an end point to detect the stenoses of a certain vascular segment. We have shown that the proposed tracking methods are robust for angiograms with various vessel structure. The automatic detection method can effectively measure the diameter of the vessel and mark the stenoses in different angiograms. Further investigation proves that the results of interactive detection method can accurately reflect the true stenoses situation. The proposed automatic method and interactive method are effective in various angiograms and can complement each other in clinical practice. The first method can be used for preliminary screening and the second method can be used for further quantitative analysis. It has the potential to improve the level of clinical diagnosis of coronary heart disease.


page 7

page 8

page 9

page 10


Two New Stenosis Detection Methods of Coronary Angiograms

Coronary angiography is the "gold standard" for diagnosing coronary arte...

Ensemble machine learning approach for screening of coronary heart disease based on echocardiography and risk factors

Background: Extensive clinical evidence suggests that a preventive scree...

Deep CardioSound-An Ensembled Deep Learning Model for Heart Sound MultiLabelling

Heart sound diagnosis and classification play an essential role in detec...

Coronary Heart Disease Diagnosis Based on Improved Ensemble Learning

Accurate diagnosis is required before performing proper treatments for c...

On Deep Neural Networks for Detecting Heart Disease

Heart disease is the leading cause of death, and experts estimate that a...

ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography

Aortic stenosis (AS) is a common heart valve disease that requires accur...

Liver Steatosis Segmentation with Deep Learning Methods

Liver steatosis is known as the abnormal accumulation of lipids within c...

Please sign up or login with your details

Forgot password? Click here to reset