Learning Based Methods for Brain Structure-Function Mapping and Disorder Classification
Understanding the connection between the brain’s structural connectivity and its functional connectivity is of immense interest in computational neuroscience. Some studies have suggested that whole brain functional connectivity is shaped by the underlying structure, the rule by which anatomy constraints brain dynamics remains an open question. In this talk, I will discuss a computational framework that identifies a joint subspace of eigenmodes for both functional and structural connectomes. We further learned the joint eigen spectra of both the connectomes in order to predict the functional connectome of a subject from the structural counterpart. In the second part of the presentation, I will discuss a deep learning framework for classification of tinnitus disease, which is an auditory phantom perceptual disorder. Motivated by the evidence of subtle anatomical or functional morphological information in magnetic resonance images (MRI) of the brain, we developed a data-driven framework for tinnitus classification (tinnitus or healthy subject) and prediction of tinnitus severity. The proposed classification method could be used for early detection, monitoring clinical trials, and tracking the progression of the disease.
Date and Time
Location
Hosts
Registration
- Date: 13 Jul 2023
- Time: 05:30 PM to 07:00 PM
- All times are (UTC+05:30) Chennai
-
Add Event to Calendar
- Seminar Room
- IIT Kharagpur
- Kharagpur, West Bengal
- India 721302
- Building: Department of Electrical Engineering
- Room Number: N208
Speakers
Dr. Sanjay Ghosh of Department of Radiology and Biomedical Imaging, University of California San Francisco (UCSF), USA
Learning Based Methods for Brain Structure-Function Mapping and Disorder Classification
Understanding the connection between the brain’s structural connectivity and its functional connectivity is of immense interest in computational neuroscience. Some studies have suggested that whole brain functional connectivity is shaped by the underlying structure, the rule by which anatomy constraints brain dynamics remains an open question. In this talk, I will discuss a computational framework that identifies a joint subspace of eigenmodes for both functional and structural connectomes. We further learned the joint eigen spectra of both the connectomes in order to predict the functional connectome of a subject from the structural counterpart. In the second part of the presentation, I will discuss a deep learning framework for classification of tinnitus disease, which is an auditory phantom perceptual disorder. Motivated by the evidence of subtle anatomical or functional morphological information in magnetic resonance images (MRI) of the brain, we developed a data-driven framework for tinnitus classification (tinnitus or healthy subject) and prediction of tinnitus severity. The proposed classification method could be used for early detection, monitoring clinical trials, and tracking the progression of the disease.
Biography:
Sanjay Ghosh received PhD in electrical engineering from IISc Bangalore in 2019 and is currently a Postdoctoral Scholar at the University of California San Francisco (UCSF), USA. His broad research interests are in computational imaging, brain signal processing, and machine learning methods for neurological disorder analysis. He received Best Student Paper Award at IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2018 and Silver Award at International Conference on Biomagnetism (BIOMAG) 2022. Dr. Ghosh is also a fellow of “DAAD Postdoc-NeT-AI 2023” program, an initiative to collaborative research with German research institutions.