We next welcome Dr. James Duncan from Yale University where he is the Ebenezer K. Hunt Professor of Biomendical Engineering.
Biomarker Detection, Brain Response Characterization and Outcome Prediction for ASD Treatment Assessment from Neuroimaging
Abstract: Functional magnetic resonance imaging (fMRI) has been shown to be helpful for the study of autism spectrum disorders (ASD). This talk will describe the evolution of efforts in this area within our Image Processing and Analysis Laboratory, that carry promise for producing objective biomarkers for ASD from both resting-state and task-based fMRI, as well as predicting patient response to a behavioral therapy known as Pivotal Response Treatment (PRT) from baseline task-based fMRI. Such biomarkers would provide an important step in better understanding the underlying pathophysiology of ASD. Patient response prediction could help with objective and personalized diagnosis, provide new targets for development of new treatments, and provide a way to monitor patient progress.
First, early image analysis efforts will be described that were based on estimating connected subnetwork membership using multi-view (structural and functional) MRI data, which developed into a more robust group-wise unified Bayesian framework to detect both hyper- and hypo-active communities within whole-brain, task-based fMRI data. Next, more recent work will be presented that has focused on deriving ASD biomarkers from both resting-state and task-based functional connectivity measures. This work was based on the classification of individual subjects (into ASD or typical control) and identifying spatially-specific key regions using either i.) recurrent neural networks with long short-term memory (LSTMs) directly from resting-state fMRI time-series using both our own data as well as the entire large, multi-site Autism Brain Imaging Data Exchange (ABIDE) I dataset for training and testing and ii.) using a 2-stage method based on convolutional neural networks (CNNs) that classifies ASD and control subjects using our own task-based fMRI images and interpreting saliency features activated by the classifier.
Finally, two approaches will be presented that predict patient response to PRT behavioral therapy, guided by the above-mentioned biomarkers. Initial efforts were based on a two-stage strategy using random forest regression and bagging. Our most recent, robust results will then be described using an LSTM- based, discriminative-generative regression strategy. This includes a data augmentation approach that is specific to region-of-interest (ROI) analysis for handling smaller data sets, and incorporates subject-specific phenotypic information by initializing the LSTM network based on each subject’s non-imaging parameters.
Bio: James S. Duncan is the Ebenezer K. Hunt Professor of Biomedical Engineering and a Professor of Radiology & Biomedical Engineering, Electrical Engineering and Statistics & Data Science at Yale University. Dr. Duncan received his B.S.E.E. with honors from Lafayette College (1973), and his M.S. (1975) and Ph.D. (1982) both in Electrical Engineering from the University of California, Los Angeles. Dr. Duncan has been a Professor of Diagnostic Radiology and Electrical Engineering at Yale University since 1983. He has been a Professor of Biomedical Engineering at Yale University since 2003, and the Ebenezer K. Hunt Professor of Biomedical Engineering at Yale University since 2007. He has served as the Acting Chair and is currently Director of Undergraduate Studies for Biomedical Engineering. Dr. Duncan’s research efforts have been in the areas of computer vision, image processing, and medical imaging, with an emphasis on biomedical image analysis and image-based machine learning. He has published over 260 peer-reviewed articles in these areas and has been the principal investigator on a number of peer-reviewed grants from both the National Institutes of Health and the National Science Foundation over the past 30 years. He is a Life Fellow of the Institute of Electrical and Electronic Engineers (IEEE), and a Fellow of the American Institute for Medical and Biological Engineering (AIMBE) and of the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society. In 2014 he was elected to the Connecticut Academy of Science & Engineering. He has served as co-Editor-in-Chief of Medical Image Analysis, as an Associate Editor of IEEE Transactions on Medical Imaging, and on the editorial boards of Pattern Analysis and Applications, the Journal of Mathematical Imaging and Vision, “Modeling in Physiology” of The American Physiological Society and the Proceedings of the IEEE. He is a past President of the MICCAI Society. In 2012, he was elected to the Council of Distinguished Investigators, Academy of Radiology Research and in 2017 received the “Enduring Impact Award” from the MICCAI Society.