سامانه همایش ها

English

صفحه اصلی / دومین کنفرانس ملی عصر انفجار تکنولوژی؛ هوش مصنوعی، تحولی در صنعت، تجارت و زنجیره تامین و دومین کنفرانس ملی علم داده در کاربردهای مهندسی

Coronary Full artery segmentation using U-Net neural network architecture

نویسندگان :

Rezvan Monjezi¹ Mahdieh Ghasemi² Mahdi Salehi³ Alireza Rowhanimanesh⁴ Samaneh Tabaee⁵

1- دانشگاه نیشابور 2- دانشگاه نیشابور 3- دانشگاه نیشابور 4- دانشگاه نیشابور 5- دانشکده علوم پزشکی نیشابور

کلمات کلیدی :

Medical image segmentation،U-Net،evaluation metrics،Angiography،Coronary artery disease

چکیده :

Coronary artery disease (CAD) ranks among the most widespread heart conditions today. The World Health Organization's recent reports show cardiovascular diseases are now claiming lives faster than any other cause globally. What happens is that plaque slowly builds up inside blood vessels condition known as atherosclerosis, causing them to narrow and stiffen over time. This progression subsequently causes ischemic changes in tissues or organs, increasing the risk of angina, myocardial infarction, and other cardiovascular events This study presents an optimized U-Net architecture for coronary artery segmentation using the ARCADE dataset, achieving 97.08% pixel accuracy (loss: 0.0810), 0.7577 precision, and 0.5702 recall. Three critical findings emerge from our analysis: 1) Metric Discrepancy, 2) Architectural Optimization, and 3) Clinical Implications. These results emphasize the need for specialized evaluation protocols in medical image segmentation, where traditional computer vision metrics must be supplemented with clinically relevant measures. The study provides concrete guidance for future ARCADE benchmark development, particularly regarding annotation standardization for thin tubular structures and the adoption of compound loss functions to address class imbalance.