No abstract

No abstract

No abstract

Atherosclerosis is the leading cause of death in the world. It is a cardiovascular disease characterized by the accumulation of inflammatory cells and lipids inside the artery walls. In Brazil, more than 30% of all deaths are due to cardiovascular diseases. The carotid intima-media thickness, obtained from ultrasound images, maybe an early estimate of atherosclerosis.This test is fast, safe and non-invasive, as well as being reproducible and relatively inexpensive. In this context, this work, based on convolutional neural networks and techniques of mathematical morphology, consists in automatically locating the region that covers the intima and media sublayers of carotid arteries. The proposed method obtained a score of 88% considering the trained model applied to 234 ultrasonographic images in two different datasets. The analysis of the neighborhood of the points obtained can be useful in the evaluation of cardiovascular risk factors.