Carotid Artery Plaque Analysis Using Deep Neural Networks for Improved Detection and Classification

Bundela, Priyanka (2024) Carotid Artery Plaque Analysis Using Deep Neural Networks for Improved Detection and Classification. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (9MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

Carotid artery one of the major blood vessels that carries oxygenated blood to the brain and that buildup of plaque in the artery can lead to serious cardiovascular disease including atherosclerosis, stroke or rupture of the arteries and all of these conditions being life-threatening. Plaque clogging the flow of oxygen to the brain causes strokes. High-penetration ultrasound scanners are commonly used to identify problems such as plaque buildup in the carotid artery, but those devices are costly. In other cases, general practitioners simply don’t have access to low-cost, low-depth ultrasound scanners and available devices tend not to provide sufficient sensitivity for plaque identification or measurement. The authors explore whether AI methods can be used to derive the same diagnostic information from low-depth ultrasound images as can be obtained with high-penetration scanners. Specifically, characteristics from the images were extracted using CNN models including U-Net, which also segmented the carotid artery and plaque sections. We used Roboflow to improve segmentation accuracy for artery and plaque detection. Additionally, SRCNN and Real-ESRGAN were used to enhance low-penetration ultrasound images. Ultimately, Linear Regression was employed to successfully determine measurements from these low-res images.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Agarwal, Bharat UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > R Medicine (General) Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	01 Sep 2025 15:37
Last Modified:	01 Sep 2025 15:37
URI:	https://norma.ncirl.ie/id/eprint/8685

Actions (login required)

View Item