Australian researchers develop AI-based test to measure progression of Alzheimer’s disease

Researchers from the Commonwealth Scientific and Industrial Research Organization, in collaboration with the Queensland University of Technology, have developed what could be the world’s first AI-based test to measure brain atrophy.

WHAT IS IT ABOUT

They used AI to create a set of artificial MRI images of the brain with predetermined signs of neurodegeneration in the cortex, the region of the brain most affected by neurodegenerative diseases such as Alzheimer’s.

The AI-powered benchmark allows researchers to quantify and locate targeted brain degeneration to test how the method of quantifying cortical thickness works.

Based The results, published in the journal Medical Image Analysis, test the sensitivity of existing methods for measuring brain atrophy to a minuscule level of just 0.01 millimeters.

WHY IS IT IMPORTANT

Cortical atrophy, or thinning of the cerebral cortex, can begin up to ten years before the onset of clinical symptoms of Alzheimer’s disease, said CSIRO scientist Dr. Philip Rusak. However, measuring its progression has been challenging since changes in the thickness of the cerebral cortex are indeed minimal.

“Extremely precise methods are needed to observe these features on brain images as they begin to appear so that they can be treated sooner rather than later,” Rusak said.

While there are AI-based methods for assessing the onset or progression of neurodegenerative diseases, there is a lack of robust datasets to test their sensitivity. The latest CSIRO development fills this particular gap.

The referenced MRI dataset is now publicly available for use by clinicians and scientists in their own evaluations of methods for quantifying cortical thickness.

CSIRO stated that their AI benchmarking method could potentially lead to “better understanding of dementia and other debilitating brain diseases.” He also added that it could be used to predict the expected level of cortical degeneration over time.

BIG TREND

There have been other technological innovations in the diagnosis of Alzheimer’s disease that have recently been reported in the Asia-Pacific region. Just last month The Korea Institute of Machinery and Materials has announced the development of an intraocular lens that could help in the early detection of Alzheimer’s disease. The artificial lens is made from a biosensitive hydrogel that exhibits a moiré pattern in response to a targeted biomarker for Alzheimer’s disease.

Last year, Fujifilm has unveiled artificial intelligence technology that predicts the progression of Alzheimer’s disease by analyzing patterns of atrophy in the hippocampus and anterior temporal lobe, as seen on 3D MRI.