CSIRO and QUT use AI to advance Alzheimer’s research

The Commonwealth Scientific and Industrial Research Organisation (CSIRO) has announced a partnership with the Queensland University of Technology (QUT) to develop a new benchmark to measure brain atrophy in neurodegenerative diseases, including Alzheimer’s disease, using artificial intelligence (AI).

Filip Rusak, research scientist from CSIRO’s Australian e-Health Research Centre, said that by leveraging machine learning technologies, his team was able to produce a set of artificial MRI images of brains with predefined signs of neurodegeneration in the cortex region.

Assessing the onset and progression of Alzheimer’s using brain magnetic resonance imaging (MRI) has traditionally been challenging, as changes in the thickness of the brain’s cortex are extremely small, often in the sub-millimetre range.

Prior to this breakthrough, the only way to get a ground truth measure of cortical thickness was by studying the brain post-mortem. However, brains begin to shrink immediately after death resulting in inaccurate readings.

“Before these findings, there was no way to conclusively determine the sensitivity of the various methods used to measure cortical thickness in Alzheimer’s patients,” Rusak said.

The scientists said this new technique allowed researchers to set the amount and location of brain degeneration they wanted to compare against, enabling them to get a clear picture of what method of cortical thickness quantification performs best.

Michael Rebsamen from The University of Bern, Switzerland said they had strong evidence that DL+DiReCT – a deep learning-based method for measuring cortical thickness – is robust and sensitive to subtle changes in atrophy.

“Until now, due to the lack of a reference MRI, we could not quantify what level of atrophy can truly be measured,” Dr Rebsamen said.

“The innovative benchmark from CSIRO closes this gap and marks an important milestone for evaluating cortical thickness methods,” he said.

Dr Rusak said the technology was developed off the back of commonly used and relatively inexpensive MRI images.

“The findings will help researchers pick the right tools for the job. The right tool increases the chances of accurately assessing disease progression,” Dr Rusak said.

“So, there’s no need for new medical infrastructure,” he said.

The CSIRO said that the synthetic dataset images have been made publicly available, so clinicians and scientists can use the synthetic images to conduct their own assessments of cortical thickness quantification methods.