Quantum-Inspired Magnetic Resonance Imaging Sequence Optimization for Detecting Neurological Diseases

Abstract

According to a research study by the National Institutes of Health, India, amagnetic resonance imaging (MRI) holds 89% diagnostic accuracy for acute stroke, while a computed tomography (CT) holds only 54%. Means there is still 11% area of improvement for accuracy measures required and there is 84% specific in identifying nerve enlargement. The possible solution is to use quantumcomputing; this is new era of technology in advanced design and implementation for computing techniques as compared with that of classical computers. With the goal of improving patient care, this is the area-of research using quantum technology to solve the neurological disorders. MRI and Microsoft’s quantum-inspired algorithms to enhance approach to detecting neurological disorders. To improve accuracy of MRI results in less time, an approach called magnetic resonance fingerprinting (MRF) was explored.This paper mainly focused on optimizing the sequence using Microsoft azure simulator. By generating an optimized pulse sequence and map to the accurate predefined patterns, able to create a solution that improves the diagnostic capability of MRI. Conventional computers will take long time to predict, but accuracy may alter. The proposed quantum-inspired optimization improved MRI diagnostic accuracy up to 92%, with faster sequence optimization compared to classical methods. This simulation-based proof of concept demonstrates potential for enhanced neurological disease detection while acknowledging current limitations such as simulator dependency and limited datasets.