Improved Automated Analysis of Coronary Doppler Echocardiograms to Predict Early Coronary Microvascular Disease

Coronary microvascular disease (CMD) is a heart condition that frequently precedes the development of more serious heart diseases. Although it can be assessed through Transthoracic Doppler echocardiography (TTDE) by observing changes in coronary blood flow patterns, manual analysis of TTDE is time consuming and subject to bias. In a previous study, a program was created to automatically analyze coronary blood flow patterns by parsing TTDE videos into a single continuous image, binarizing and separating the image into distinct cardiac cycles, and extracting characteristic data values from each cycle. The program significantly reduced variability and time to complete analysis, but obstacles such as interfering noise and varying video sizes left room to increase the program's accuracy. The goal of this study was to improving the program's ability to handle challenging video variations and to remove unnecessary manual intervention to further reduce analysis time. To confirm this improved analysis, several videos were analyzed using both the original MATLAB program and updated Python program. Comparison of specific examples showed the new program was better able to identify and remove difficult noise objects, and more consistently and fully captured the Doppler region. This improved analysis has the potential to provide more insight into the early diagnosis of unhealthy coronary flow by offering a quick, easy, and accurate method of analysis.No embargoAcademic Major: Computer Science and Engineerin