Decoding the brain to treat neurodegenerative disorders
Published on 27 June 2024
A/Prof Helen Zhou advances research on the intricate human brain with an innovative predictive, precise and personalised approach.
A/Prof Helen Zhou estimates that there is still about 95 per cent that is unknown about the human brain. The curiosity to uncover more “secrets” of human brain has always piqued her interest and inspired her fellow lab colleagues at the NUS Yong Loo Lin School of Medicine (NUS Medicine).
While studying the brain might seem an unlikely pursuit for someone with a background in computer science, it was A/Prof Zhou’s growing interest in algorithms, neuronal networks and image processing — which developed while she was working on her PhD — that led her down the path of machine learning and its uses in brain imaging. The goal? To utilise her expertise with algorithms to help people with dementia.
Since receiving her PhD, she has done a post-doctoral fellowship at the Memory and Aging Center, Department of Neurology, University of California, San Francisco, where she researched neuroscience and neuropsychiatric disorders. She also worked as an associate research scientist at New York University’s Department of Child and Adolescent Psychiatry.
Today, she runs the neuroimaging lab at NUS’s Centre for Sleep and Cognition (CSC) & Centre for Translational MR Research (TMR), studying multimodal neuroimaging in neuropsychiatric disorders. In plainer terms, her research allows her to better understand how to spot certain ageing-related disorders in the brain through machine learning, neuroimaging and other techniques. Being able to understand brain network characteristics — and how different regions of the brain talk to each other — not only provides information on present conditions but has the potential to reveal future health issues.
A predictive approach is key to the future of healthcare
A/Prof Zhou’s research is more focused on identifying individuals at risk for dementia due to neurodegenerative and/or cerebrovascular diseases and predict their disease progression using brain imaging and artificial intelligence (AI).
“We can actually take a snapshot of your brain and tell you whether you are at risk in the next five years,” she explained. Though further development is needed, being able to detect diseases early is one way to ease the burdens on the healthcare system in the future.
A predictive approach is not enough – precision matters
According to A/Prof Zhou, a patient’s prognosis or risk profile for degenerative diseases can differ due to the many differences in the way their brain might be wired, or its “network organisation”. Instead of looking at a single region or node to understand how someone’s brain might behave, it is essential to get a complete picture of the way different brain nodes “talk” to each other. “Brain imaging can define our vulnerability to disease, therefore it’s important to have a precise approach in terms of understanding brain structure and functionality,” she explained.
She refers to this structure and functionality as the “brain network phenotype”, which is the central hypothesis that her neuroimaging lab seeking to answer. In developing a machine learning algorithm, her hope is that this precise approach to mapping and learning how the various parts of our brain function as a whole will help with the diagnosis of ageing-related disorders like dementia and its prognosis.
In stratifying patients, environmental factors — especially those that can be changed — should also be accounted for. A/Prof Zhou also noted that cerebrovascular issues are more common in Asia than in Western countries. These conditions that affect blood flow and blood vessels in the brain can lead to a higher incidence of dementia. Her team, working with other colleagues across the island, is hoping to investigate how neurodegenerative and cerebrovascular processes interact; importantly, identify ways to prevent or slow down cognitive decline.
With her work to integrate AI with brain imaging and other assays, A/Prof Zhou hopes that the future of predicting dementia will be more personalised, precise and scalable to a larger population.
In consultation with A/Prof Helen Zhou, Associate Professor, Centre for Sleep and Cognition, and Director, Centre for Translational Magnetic Resonance Research, NUS Medicine; and Associate Professor, Department of Electrical and Computer Engineering, College of Design and Engineering, Human Potential Translational Research Program and Department of Medicine, NUS Medicine.
