EE Seminar: Big data - small training set: biomedical image analysis bottlenecks, some strategies and applications
(The talk will be given in English)
Speaker: Dr. Tammy Riklin-Raviv
Department of Electrical and Computer Engineering, Ben Gurion University
Monday, June 26th, 2017
15:00 - 16:00
Room 011, Kitot Bldg., Faculty of Engineering
Big data - small training set: biomedical image analysis bottlenecks, some strategies and applications
Recent progress in imaging technologies leads to a continuous growth in biomedical data, which canprovide better insight into important clinical and biological questions. Advanced machine learning techniques, such as artificial neural networks are brought to bear on addressing fundamental medical image computing challenges such as segmentation, classification and reconstruction, required for meaningful analysis of the data. Nevertheless, the main bottleneck, which is the lack of annotated examples or ‘ground truth’ to be used for training, still remains.
In my talk, I will give a brief overview on some biomedical image analysis problems we aim to address, and suggest how prior information about the problem at hand can be utilized to compensate for insufficient or even the absence of ground-truth data. I will then present a framework based on deep neural networks for the denoising of Dynamic contrast-enhanced MRI (DCE-MRI) sequences of the brain. DCE-MRI is an imaging protocol where MRI scans are acquired repetitively throughout the injection of a contrast agent, that is mainly used for quantitative assessment of blood-brain barrier (BBB) permeability. BBB dysfunctionality is associated with numerous brain pathologies including stroke, tumor, traumatic brain injury, epilepsy. Existing techniques for DCE-MRI analysis are error-prone as the dynamic scans are subject to non-white, spatially-dependent and anisotropic noise. To address DCE-MRI denoising challenges we use an ensemble of expert DNNs constructed as deep autoencoders, where each is trained on a specific subset of the input space to accommodate different noise characteristics and dynamic patterns. Since clean DCE-MRI sequences (ground truth) for training are not available, we present a sampling scheme, for generating realistic training sets with nonlinear dynamics that faithfully model clean DCE-MRI data and accounts for spatial similarities. The proposed approach has been successfully applied to full and even temporally down-sampled DCE-MRI sequences, from two different databases, of stroke and brain tumor patients, and is shown to favorably compare to state-of-the-art denoising methods.
Tammy Riklin Raviv is a faculty member at the Electrical and Computer Engineering department of Ben-Gurion University of the Negev since 2012. Her research focuses on the development of computational tools for processing and analysis of medical, and biological images. She holds a B.Sc. in Physics and an M.Sc. in Computer Science from the Hebrew University of Jerusalem. She received her Ph.D. from the School of Electrical Engineering of Tel-Aviv University. In 2010-2012 she was a research fellow at Harvard Medical School and the Broad Institute. Prior to this (2008-2010) she was a post-doctorate associate at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology.