Babak Afshin Pour, PhD
Babak Afshin-Pour is currently a postdoctoral fellow at Baycrest hospital, which is fully affiliated with University of Toronto. He received a B.S degree in biomedical engineering and M.S. and PhD degrees in electrical engineering from University of Tehran.
His research interests in electrical engineering are in the areas of advanced medical signal and image processing especially developing new techniques in functional MRI (fMRI) data processing, exploring different approaches for evaluation of the analysis techniques, and optimizing fMRI data processing pipeline.
Within the growing number of applications of functional magnetic resonance imaging (fMRI) in neuroscience and in the clinical domain for evaluation of individual treatments, there is a need to enhance the quality of the results.
We proposed a novel approach for evaluating the performance of activation detection in real (experimental) datasets using a new mutual information (MI)-based metric. The proposed approach is based on measuring the approximate MI between the fMRI time-series of a validation dataset and a calculated activation map (thresholded label map or continuous map) from an independent training dataset. The MI metric is used to measure the amount of information preserved during the extraction of an activation map from experimentally related fMRI time-series. The processing method that preserves maximal information between the maps and related time-series is proposed to be superior.
Another key aspect of an fMRI experiment is reproducibility and it requires that the same local activation maps are likely to be observed in experimental replications.
PhD, Electrical Engineering, University of Tehran
3560 Bathurst Street, Toronto, Ontario, Canada. M6A 2E1 Phone: 416-758-2500 ext. 2001 Email: bafshinpourresearch.baycrest.org