BME’s Joyita Dutta and Colleague Obtain NIH Award for Pioneering Research to Predict Alzheimer’s Disease
Alzheimer's Disease, a debilitating and degenerative brain disease that has no cure, affects approximately 5.8-million people in the United States, but early detection is the most promising approach. Now, principal investigator (PI) Joyita Dutta of the Biomedical Engineering Department is collaborating with project leader and PI Ina Fiterau Brostean of the College of Information and Computer Sciences to develop some groundbreaking new techniques for extremely early detection of Alzheimer’s disease. Their trailblazing project has attracted a $287,118 R03 collaborative award from the National Institutes of Health.
The various modes of data being studied and incorporated by Dutta and Brostean include genetic information, brain MRIs, and cognitive tests, with a focus on screening for Alzheimer’s disease in the general population.
The cutting-edge project represents what Dutta and Brostean call “a striking advance that will enable clinicians to identify new prevention strategies and prepare for, rather that respond to, Alzheimer’s.” The UMass researchers will make this advance possible with their novel method to identify the onset of the disease years before symptoms begin to appear.
According to Dutta and Brostean, “We will introduce new techniques, based on deep-transfer learning, to extract representations from brain MRIs, applicable to prospectively collected data... We will incorporate the feature extraction in an end-to-end predictive framework using multimodal deep learning.”
Dutta and Brostean explain that their method will be especially useful for modeling, monitoring, and forecasting the progression of Alzheimer's disease in which “MRIs accompany the clinical information collected at different levels of granularity.”
As Dutta and Brostean say, “We will start with a model that predicts the evolution of Alzheimer’s disease, trained on multimodal longitudinal data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study.”
According to the NIH, “The ADNI is an ongoing, longitudinal, multicenter study designed to develop clinical, imaging, genetic, and biochemical biomarkers for the early detection and tracking of Alzheimer's disease.”
Dutta and Brostean say that they will develop ‘convolutional-neural-network-based models’ that work directly with brain MRIs, optimized to capture the predictive capabilities of the engineered features present in the ADNI.
According to intel.com, “A convolutional neural network is a type of deep-learning algorithm that is most often applied to analyze and learn visual features from large amounts of data.”
Beyond that, Dutta and Brostean will integrate the brain MRI network with a forecasting model that uses deep learning to extract abstract representations of patients' health status based on their multimodal information, including demographics, genetic information, cognitive-test scores, and brain MRIs.
“Moreover,” say Dutta and Brostean, “we introduce methodology for the seamless transfer of the models between datasets collected as part of different studies, where the recorded information, including clinical tests, images collected, and subject questionnaires, differs across study cohorts.”
The results of this project, as being engineered by Dutta and Brostean, promise to predict the onset of Alzheimer’s disease in patients long before they begin to experience symptoms, thus allowing for the earliest, most-comprehensive preparation and treatment available today. (November 2023)