Machine learning techniques for microwave brain stroke detection and classification
Thesis type EXPERIMENTAL AND SIMULATIONS, MASTER THESIS, MULTIDISPLINARY
Description Stroke is a brain injury that occurs when oxygen-rich blood supply to the brain is interrupted, causing a severe damage in the affected area and leading to transitory or permanent disability or even death. It is triggered when a blood vessel of the brain either bursts (or ruptures) or is blocked by a clot. Strokes represent a critical medical emergency and adequate and prompt diagnosis and treatment are essential to raise the probability of recovery and reducing the patients’ damages, the risk of death, or further disabilities.
The main objective of this Master Thesis is to investigate the use of machine learning (ML) techniques to detect and classify brain strokes. The input data are measured via a custom microwave system available at the Antenna and EMC Lab, DET. The system is placed conformal to head phantoms, that have the same electric characteristics as the human head tissues at microwave frequencies. Depending on the background of the Candidate, the acceleration of the selected ML algorithms with software or dedicated hardware design methods will be considered in the Thesis.
Main reference: J. A. Tobon Vasquez, R. Scapaticci, G. Turvani, G. Bellizzi, D. O. Rodriguez-Duarte, N. Joachimowicz, B. Duchêne, E. Tedeschi, M. R. Casu, L. Crocco, F. Vipiana, “A Prototype Microwave System for 3D Brain Stroke Imaging”, SENSORS, Special Issue on Microwave Sensing and Imaging, 2020, 20, 2607 [DOI: 10.3390/s20092607].
Notes Expected duration: 6 months.
Deadline 03/12/2024 PROPONI LA TUA CANDIDATURA