Making MRI faster
Mevan Ekanayake, Making MRI faster
Winner – Monash University VYT local competition (2022)
Magnetic Resonance Imaging (MRI) provides the most accurate medical images inside the human body and is often utilized by radiologists and medical practitioners to search for abnormalities, make diagnoses, and recommend treatment options. However, the scan time in MRI can easily exceed 30 minutes which leads to low patient throughput, problems with patient comfort and compliance, artefacts from patient motion, and high examination costs. In our research, we employ Artificial Intelligence (AI) to reduce the scan time of MRI. This would be beneficial not only to patients in critical conditions requiring quick scans but also to vulnerable groups such as pregnant women, elderly persons, small children, and persons suffering from special conditions such as Parkinson's disease, Claustrophobia, etc. Achieving faster scan times will also increase throughput and reduce complications in resource allocation in regional areas where accessibility to MRI scanners is scarce. Our methodology involves combining MRI physics with AI to build deep learning models which could produce high-quality MR images utilising undersampled raw MRI measurements as input. The outputs of our research will fundamentally reduce risks and costs in MRI.