Making a difference 2020-2021

ARTIFICIAL INTELLIGENCE IMPROVING THE STUDY OF BRAIN DISEASE A team of Macquarie University neurosurgery and computer science researchers, including ARC Future Fellow, Professor Antonio Di Ieva, is investigating the use of Artificial Intelligence and other computer tools to improve the study of brain disease, with results already indicating far-reaching impact for disease diagnosis and treatment. The research is taking place at the University’s world-first Computational NeuroSurgery (CNS) Laboratory founded by Professor Antonio Di Ieva, who is also a practising neurosurgeon at Macquarie University Hospital. The CNS lab is focused on developing computerised tools to produce more accurate images of the brain and its diseases. ‘Our research is to develop new computer methods to identify novel diagnostic, prognostic and therapeutic markers of brain diseases, such as brain tumours and cerebrovascular diseases,’ Professor Di Ieva says. In their latest research, the team used an AI method called Deep Learning to analyse surgical samples of gliomas – the most common primary brain tumours – and to predict patient outcome and treatment. By using Deep Learning to analyse surgical samples of gliomas, this allows a much faster and cheaper way to predict the presence of an important DNAmarker for the disease, improving and speeding up the treatment of patients affected by brain cancer. Professor Di Ieva andMacquarie Medical Imagingwere also the first in Australia to introduce a Magnetic Resonance technique called 2HG-Magnetic Resonance Spectroscopy to predict the status of such a gene even before surgery. ‘The long-term goal is to enhance treatment and outcomes for patients.’

A NEW WORLD-FIRST AI-DRIVEN NEUROSURGERY LAB AT MACQUARIE

UNIVERSITY HOSPITAL IS USING A MAGNETIC RESONANCE TECHNIQUE TO PRODUCE MORE ACCURATE IMAGES OF THE BRAIN, IMPROVING OUTCOMES FOR PATIENTS.

Professor Antonio Di leva. Credit: Macquarie Neurosurgery.

74

IMPROVING HEALTH ANDWELLBEING

Made with FlippingBook Converter PDF to HTML5