Sanjay Ghosh



Email: sanjay.ghosh at ucsf.edu

Google-scholar

LinkedIn

I am a Postdoctoral Scholar in the Department of Radiology and Biomedical Imaging at the University of California San Francisco (UCSF), USA. My broad research interests are in computational imaging, brain data analysis, and machine learning. I obtained the PhD degree in electrical engineering from the Indian Institute of Science in 2019. My current research projects at UCSF are in MEG/EEG brain source imaging, brain connectivity analysis, and deep learning-based brain disorders analysis.

My doctoral thesis was on the developing novel computational algorithms for kernel filtering in image processing and then exploring its various imaging applications including denoising of images, reconstruction from limited measurements by camera sensors, artifact reduction in image compression, lowlight imaging etc. The thesis received several international recognition:

Best Student Paper Award, IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2018.

• Finalist, Best Student Paper Awards, National Conference on Communications (NCC) 2019.

• Finalist, Best Student Paper Awards, Int’l Conf. on Signal Proc. and Comm. (SPCOM) 2016.

In addition, the thesis was nominated for a short oration at IEEE International Conference on Image Processing (ICIP) 2019 and for the Doctoral Consortium at SIGGRAPH Asia 2019.


News

• Mar 15, 2023: Received travel grant to attend IEEE ISBI 2023 to be held in Cartagena, Colombia.

• Mar 13, 2023: An abstract got accepted at OHBM 2023 to be held in Montréal, Canada.

• Feb 22, 2023: Delivered a talk (zoom) at Imperial College London, UK.

• Jan 27, 2023: Delivered a talk (in-person) at Indian Institute of Science, Bangalore, India.

• Jan 22, 2023: Two papers got accepted at IEEE ISBI 2023.


Positions

Sep 2020 - Present: Postdoctoral Scholar, University of California San Francisco, USA.

Mar 2020 - Sep 2020: Postdoctoral Scholar, Pennsylvania State University, USA.

Aug 2019 - Mar 2020: Visiting Scholar, University of Iowa, USA.

Aug 2013 - Jul 2014: Lecturer, National Institute of Technology Jamshedpur, India.


Education

2019: PhD - Electrical Engineering, Indian Institute of Science, India.

2013: M.Tech - Electrical Engineering, Indian Institute of Technology Madras, India

2011: B.Tech - Electronics and Communcation Engineering, West Bengal University of Technology, India.



Publications

In-Preparation / Under-review

Q1. S. Ghosh, C. Cai, Y. Gao, A. Hashemi, S. Haufe, K. Sekihara, A. Raj, and S. Nagarajan, "Joint estimation of sparse sources and low-rank noise for electromagnetic brain imaging".


JOURNALS

J11. C. Cai, Y. Long, S. Ghosh, A. Hashemi, B. Chen, Y. Gao, M. Diwakar, S. Haufe, K. Sekihara, W. Wu, and S. S. Nagarajan, "Bayesian adaptive beamformer for robust electromagnetic brain imaging of correlated sources in high spatial resolution," IEEE Transactions on Medical Imaging.

J10. S. Ghosh, A. Raj, and S. S. Nagarajan, "A Joint Subspace Mapping Between Brain Structural and Functional Connectomes," NeuroImage. [bioRxiv]

J9. S. Ghosh and A. Garai, "Image downscaling using nonlocal co-occurrence," Journal of Visual Communication and Image Representation.

J8. T. Lin†, S. Ghosh†, L. B. Hinkley, C. L. Dale, A. Souza, J. H. Sabes, C. P. Hess, M. E. Adams, S. W. Cheung, and S. S. Nagarajan, Multi-tasking deep network for tinnitus classification and severity prediction from multimodal structural MR images, Journal of Neural Engineering, 2022. (†: equal contributions)

J7. A. Hashemi, C. Cai, Y. Gao, S. Ghosh, K.-R. Müller, S. S. Nagarajan, and S. Haufe, Joint learning of full-structure noise in hierarchical Bayesian regression models, IEEE Transactions on Medical Imaging, 2022.

J6. S. Ghosh, R. G. Gavaskar, D. Panda, and K. N. Chaudhury, Fast scale-adaptive bilateral texture smoothing, IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 7, pp. 2015 - 2026, 2020.

J5. S. Ghosh, P. Nair, and K. N. Chaudhury, Optimized Fourier bilateral filtering, EEE Signal Processing Letters, vol. 25, no. 10, pp. 1555-1559, 2018.

J4. S. Ghosh and K. N. Chaudhury, Artifact reduction for separable nonlocal means, Journal of Electronic Imaging, vol. 26, no. 6, pp. 063012: 1-6, 2017..

J3. S. Ghosh, A. K. Mandal, and K. N. Chaudhury, Pruned non-local means, IET Image Processing, vol. 11, no. 5, pp. 317-323, 2017.

J2. S. Ghosh and K. N. Chaudhury, Fast separable non-local mean, Journal of Electronic Imaging, vol. 25, no. 2, pp. 023026: 1- 14, 2016.

J1. S. Ghosh and K. N. Chaudhury, On fast bilateral filtering using Fourier kernels, IEEE Signal Processing Letters, vol. 23, no. 5, pp. 570-574, 2016.


CONFERENCES (PROCEEDING)

C13. S. Ghosh, E. Bhargava, C.T. Lin, and S. Nagarajan, "Graph Convolutional learning of multimodal brain connectome data for schizophrenia classification," IEEE International Symposium on Biomedical Imaging (ISBI, 2023.

C12. S. Ghosh, C. Cai, Y. Gao, A. Hashemi, S. Haufe, K. Sekihara, A. Raj, and S. Nagarajan, "Bayesian inference for brain source imaging with joint estimation of structured low-rank noise," IEEE International Symposium on Biomedical Imaging (ISBI), 2023.

C11. A. Hashemi, Y. Gao, C. Cai, S. Ghosh, K.-R. Müller, S. Nagarajan, and S. Haufe Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging, Advances in Neural Information Processing Systems (NeurIPS), 2021.

C10. M. Mani, H. K. Aggarwal, S. Ghosh, and M. Jacob, “, Model-based deep learning for reconstruction of joint k-q under-sampled high resolution diffusion MRI, Proc. IEEE International Symposium on Biomedical Imaging (ISBI), pp. 913-916, Iowa City, USA, 2020.

C9. S. Ghosh and K. N. Chaudhury, Fast bright-pass bilateral filtering for low-light enhancement, Proc. IEEE International Conference on Image Processing (ICIP), pp. 205-209, Taipei, Taiwan, 2019.

C8. S. Ghosh, R. G. Gavaskar, and K. N. Chaudhury, “, Saliency guided image detail enhancement, Proc. National Conference on Communications (NCC), Bangalore, India, 2019. (Finalist, Best Student Paper Awards)

C7. Unni V. S., S. Ghosh, and K. N. Chaudhury, Linearized ADMM and fast nonlocal denoising for efficient plug-and-play restoration, Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 11-15, California, USA, 2018. (BEST STUDENT PAPER AWARD)

C6. S. Ghosh and K. N. Chaudhury, Color bilateral filtering using stratified Fourier sampling, Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 26-30, California, USA, 2018.

C5. S. Ghosh and N. Tripathi, Guided filtering of hyperspectral images, Proc. IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1954-1962, Lake Tahoe, USA, 2018.

C4. S. Ghosh, S. Nayak, and K. N. Chaudhury, Lucky DCT aggregation for camera shake removal, Proc. IEEE International Conference on Image Processing (ICIP), pp. 3790-3794, Beijing, China, 2017.

C3. S. Ghosh and K. N. Chaudhury, Fast bilateral filtering of vector-valued images, Proc. IEEE International Conference on Image Processing (ICIP), pp. 1823-1827, Arizona, USA, 2016.

C2. S. Ghosh and K. N. Chaudhury, Fast and high-quality bilateral filtering using Gauss-Chebyshev approximation Proc. International Conference on Signal Processing and Communications (SPCOM), Bangalore, India, 2016. (Finalist, Best Student Paper Awards)

C1. S. Ghosh and A. P. Kannu, Relay placement and spectrum sharing strategies for soft and fractional frequency reuse schemes, Proc. National Conference on Communications (NCC), India, 2015.

CONFERENCES (ABSTRACT)

A4. S. Ghosh, A. Raj, and S. Nagarajan, "Estimating brain functional connectivity from common subspace mapping between structural and functional connectomes," Society for Neuroscience, San Diego, Nov 12- 16, 2022. .

A3. S. Ghosh, C. Cai, Y. Gao, A. Hashemi, F. Jiang, S. Haufe, K. Sekihara, and S. Nagarajan, "Joint estimation of sparse sources and low-rank noise for electromagnetic brain imaging", International Conference on Bioelectromagnetism, Birmingham, Aug 28 - Sep 01, 2022.

A2. C. T. Lin†, S. Ghosh†, L. B. Hinkley, C. L. Dale, A. Souza, M. E. Adams, S. W. Cheung, and S. Nagarajan, "Multimodal convolutional network for tinnitus classification and severity prediction from structural MR images," Cognitive Neuroscience Society (CNS) 29th Annual Meeting, San Francisco, March 25-28, 2022. (†: equal contributions)

A1. A. Hashemi, C. Cai, Y. Gao, S. Ghosh, K.-R. Müller, S. Nagarajan, and S. Haufe, "Novel Techniques for Noise Estimation in Electromagnetic Brain Source Imaging", International Conference on Bioelectromagnetism, May 21-26, 2021.


Teaching

I had the opportunity to teach both undergraduate and graduate students as both an independent instructor and teaching assistant(TA).

Courses taught as Instructor, National Institute of Technology Jamshedpur, India:

– Digital Image Processing (Spring ’14 / UG).

– Wireless Communications (Spring ’14 / UG).

– Optimization Techniques (Fall ’13 / Graduate).

– Computer Architecture and Operating Systems (Fall ’13 / UG) (Co-taught).

Teaching Assistant:

– Dynamics of Linear Systems (Fall ’16 / Graduate) at Indian Institute of Science.

– Computer Organization & Microprocessors (Spring ’13 / UG) at IIT Madras.


Awards

• Silver Award, "Ketamine in depression” data analysis competition, International Conference on Biomagnetism (BIOMAG), 2022.

• Merit-Cum-Mean Scholarship, Government of West Bengal, India, (2007-2011).

• Merit Fellowship, West Bengal University of Technology, Kolkata, India, (2007-2011).

• National Merit Scholarship, Govt. of India, (2004 -2006).

The template is by Vasilios Mavroudis. Thanks!