Leveraging Image Processing and AI for Increased Sensitivity in Atherosclerosis Assessment
Brief Description of Project:
Background: In a prior study, CT scans were performed on mummies from diverse ancient populations to assess the prevalence of atherosclerosis. Atherosclerosis, characterized by the buildup of plaques in arteries, is linked to modern cardiovascular diseases.
Proposed Enhancement: We propose an innovative immersion experience to enhance the sensitivity of atherosclerosis assessment in ancient mummies using advanced image processing and artificial intelligence (AI) techniques. By employing state-of-the-art image analysis algorithms, we aim to extract more nuanced information from CT scans, improving the detection and characterization of calcified plaques.
Experience with Python and medical terminology. Interest in archeology and medicine. Interest in working with mummy imaging data.
Nature of Supervision:
Graduate student and faculty mentorship.
A Brief Research Plan (period is for 10 weeks):
Weeks 1: Data orientation and preprocessing.
Weeks 2-6: Data annotation and quality assurance.
Weeks 7-8: Algorithm development and initial machine learning model training.
Weeks 9-10: Paper preparation for the SPIE Conference
Number of Open Slots: 2
Name: Bennett Landman
Department: Electrical and Computer Engineering