This is Pradeep. I am currently working as a Postdoctoral fellow at the Rotman Research Institute, Baycrest affiliated with University of Toronto. I am currently working on study and development of optimal and reproducible fMRI preprocessing workflows with Prof. Stephen Strother. I am also interested in the development of machine learning techniques for medical image analysis. In particular, I worked on the development of statistical learning techniques for the early detection of Alzheimer’s disease as well as differential diagnosis of various neurodegenerative diseases.
During my Ph.D., I worked with Prof. Mirza Faisal Beg. Some of my developments include novel imaging biomarkers, called ThickNet features (http://www.sciencedirect.com/science/article/pii/S0197458014005521), based on graph-theoretical network analysis of inter-regional covariation in cortical thickness, which show promise for the early detection of Alzheimer's disease. You can find the related publications in this direction here (http://www.sciencedirect.com/science/article/pii/S2213158214001417) and here (http://ieeexplore.ieee.org/abstract/document/7552334/).
Another exciting area of research I am working on is the development of imaging-based biomarkers for the subclassification of MCI (classification of MCI subtypes), which can potentially lead to earlier screening of Alzheimer's disease. A publication in this direction can be found here: http://journal.frontiersin.org/Journal/10.3389/fneur.2014.00076/abstract .
I have also worked on developing multi-class differential diagnosis techniques, that can pave way for minimized misdiagnosis. One such application I worked is on three-class differential diagnosis between Alzheimer's disease, Frontotemporal disease and healthy controls. A publication in this direction can be found here: http://journal.frontiersin.org/Journal/10.3389/fneur.2014.00071/abstract.