We propose an automatic diagnostic model for left ventricular aneurysm after myocardial infarction. A epicardium segmentation model was established by mixing 2- and 3-chamber images of 90 healthy volunteers, and the dice in all cohorts exceeded 0.95. Five heartphaseimages around end-systolic and end-diastolic stages, multiplied by the predicted mask using the segmentation model were used as the input of the classification model. Data from 259 AMI patients were divided into training cohort (206) and independent testing cohort (53). ResNet was selected to extract the features of 2- and 3- chamber data. Finally, AUC achieved on 0.987/0.946 in training and testing cohort. The automtic deep learning model can be used as a scheme to dignose LVA after AMI, and has potential clinical value for early detection of the risk of the ventricular aneurysm in AMI patients.
This abstract and the presentation materials are available to members only; a login is required.