We live in a world which is naturally organized into intrinsic network structures, for example the human genome, social networks, wireless communication networks, to name a few. The study of networks is thus very relevant to modern day data-science, as we gain a lot of insight into otherwise mysterious phenomena. One such complex network is in fact, the human brain. Recently, there has been a lot of interest in understanding how regions in the brain communicate with each other and how these communication patterns influence our behavior and health. This sets us up for an important, yet really challenging question in healthcare: of how to represent these interactions and relate them to meaningful diagnostics. In light of this, my talk will highlight two of my ongoing projects which develop novel machine learning tools to represent brain functional (rs-fMRI) and structural (DTI) connectivity and relate this data-viewpoint to behavioral deficits in patients.
For the first part of my talk, I will develop a joint network optimization framework to predict clinical severity from resting state fMRI data. This model is based on two coupled terms: a generative matrix factorization and a discriminative regression framework. One of the main novelties of this algorithm lies in jointly optimizing the representation learning and prediction task, which is key to the generalization onto unseen examples. Building off of this framework, I will then introduce an extension of these general principles to incorporate multimodal information from Diffusion Tensor Imaging (DTI) and dynamic functional connectivity (rs-fMRI). At a high level, our generative matrix factorization now estimates a time-varying functional decomposition guided by anatomical connections in a graph regularization setting. We couple this representation with a deep network to predict multidimensional clinical characterizations. This deep network consists of an LSTM to model temporal-attention based dynamics of scan evolution and an ANN for prediction.
Holistically, these models help us develop a more comprehensive picture of brain connectivity and behavior. Overall, these frameworks make minimal assumptions and can potentially find a broad range of applications outside of the medical realm.
Niharika is a PhD candidate in the department of Electrical and Computer Engineering. Her research interests lie at the intersection of deep learning, non-convex optimization, manifold learning and graph signal processing applied to neuroimaging data. She has developed novel machine learning algorithms that predict behavioral deficits in patients with Autism by decoding their brain organization from their functional and structural neuroimaging scans. Prior to joining Hopkins, she obtained a bachelor’s degree (B. Tech with Hons.) in Electrical Engineering with a minor in Electronics and Electrical Communications Engineering from the Indian Institute of Technology, Kharagpur.