Vijaya Kolachalama’s Algorithm Makes Advancements In Alzheimer’s Detection
Different people have different symptoms, and so it is hard to get a precise diagnosis of Alzheimer’s disease. It is even harder to predict the likelihood of an individual afflicting the disease.
Vijaya Kolachalama, an Assistant Professor at Boston University School of Medicine and Junior Faculty Fellow and Research Fellow at the Hariri Insititute for Computing, was featured in The Brink for his work, which is helping to make that prediction easier and more specific, with the development of a deep learning algorithm.
About the Project
Vijaya Kolachalama along with his team of researchers, including Rhoda Au (BU Professor of Anatomy & Neurobiology), a Hariri Institute Research Fellow and Steering Committee member, has developed an algorithm based on Artificial Intelligence (AI) that can not only precisely predict the risk for but also diagnose Alzheimer’s disease while using a combination of brain magnetic resonance imaging (MRI), testing to measure cognitive impairment, accompanied with demographic data such as age and gender. The team used the MRI scans and clinical information of individuals with Alzheimer’s and the ones with normal cognition from one of the four national cohorts to develop a novel deep learning model to predict Alzheimer’s disease risk. The model could accurately predict the disease status on the other independent cohorts. An international team of expert neurologists was then asked to detect Alzheimer’s disease on the same set of cases. In comparison, the algorithm model performed slightly better than the average neurologist. According to researchers, this study has broad implications for expanding into the use of neuroimaging data to accurately detect the risk of Alzheimer’s disease at the point of care.
The project was supported by the National Center for Advancing Translational Sciences, National Institutes of Health, the American Heart Association, and a Hariri Research Award from the Rafik B. Hariri Institute for Computing and Computational Science & Engineering at Boston University.
About Assistant Professor Kolachalama
Vijaya Kolachalama is a faculty member within the Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine. His group leverages novel image processing and machine learning frameworks for digital pathology analysis and biomarker development, with current projects focused within the cardiovascular, renal, and cancer domains. His group also focuses on the fusion of biophysical computational modeling and machine learning to efficiently quantify the mechanisms of endovascular therapies. Before joining BU, Dr. Kolachalama held appointments as a Postdoctoral Associate at MIT, as an ORISE Fellow at the US Food and Drug Administration, and as a Principal Member of Technical Staff at the Charles Stark Draper Laboratory. He has a bachelor’s degree in Aerospace Engineering from the Indian Institute of Technology, Kharagpur, India, and a Ph.D. in Mechanical Engineering from the University of Southampton, UK. He was selected as an Institute Research Fellow in January 2017.