Using deep learning technology to make individualised inferences in brain-based disorders

Brain-based disorders, including psychiatric and neurological illnesses, represent 10.4% of global disease. At present, objective tools for detecting and monitoring brain disorders are not available. 

Deep learning is an area of artificial intelligence which allows detection of complex and distributed patterns in data that are difficult to capture using existing approaches. We will assemble a very large dataset of neuroimaging data from more than 12,000 disease-free people and more than 2,000 patients with psychosis. Using deep learning technology we will develop a model of the disease-free brain across different ages and genders and illustrate how this model can be used to detect neuroanatomical alterations and inform clinical assessment in individual patients. 

This will lead to the development of a flexible web-based tool for measuring neuroanatomical alterations in any brain-based disorders. This could help clinicians assess the presence of a disease, monitor its progression and optimise treatment in individual patients.