Joyita Dutta

Professor

Dr. Dutta’s research interests include applying cutting-edge deep learning knowledge for (1) medical image enhancement, e.g., PET image denoising and super-resolution, (2) disease diagnosis/prognosis, e.g., forecasting the spatiotemporal trajectories of tau deposition in Alzheimer’s disease, and (3) biomarker discovery, e.g., using deep learning to discover novel sleep-based predictors of age-related cognitive decline and dementia.

Current Research

Dr. Dutta directs the Biomedical Imaging and Data Science Laboratory (BIDSLab) at UMass Amherst, which develops machine learning and signal processing techniques to solve biomedical problems. Her research encompasses a broad array of biomedical data types including (1) images (e.g., positron emission tomography – PET and magnetic resonance imaging – MRI), (2) time series (electroencephalography – EEG, electrocardiography – ECG, and accelerometry), and (3) graphs (structural and functional networks of the human brain). A sizable part of Dr. Dutta’s current research effort is directed toward the development of innovative deep learning tools for Alzheimer’s biomarker discovery and progression modeling with support from a variety of federal (including NIH R01, R21, and R03), foundation, and corporate awards.

Learn more at umass.edu/engineering/about/directory/joyita-dutta

Academic Background

Postdoctoral Fellowship, 2011-2013, Massachusetts General Hospital and Harvard Medical School
PhD 2011, University of Southern California, Electrical Engineering
MS 2006, University of Southern California, Electrical Engineering
BTech 2004, Indian Institute of Technology Kharagpur, Electronics and Electrical Communication Engineering

expand

Publications

Song T-A, Chowdhury SR, Malekzadeh M, Harrison S, Blackwell Hoge T, Redline S, Stone KL, Saxena R, Purcell SM, Dutta J. AI-driven sleep staging from actigraphy and heart rate. PLOS One, 2023.

Bradshaw T, McCradden M, Jha AK, Dutta J, Saboury B, Siegel E, Rahmim A. Artificial intelligence algorithms need to be explainable – or do they? J Nucl Med, 2023; 64 (6) 976-977.

Saboury B, Bradshaw TJ, Boellaard R, Buvat I, Dutta J, Hatt M, Jha AK, Li Q, Liu C, McMeekin H, Morris M, Scott PJH, Siegel E, Sunderland JJ, Pandit-Taskar N, Wahl R, Zuehlsdorff S, Rahmim A. Artificial intelligence in nuclear medicine: Opportunities, challenges, and responsibilities toward a trustworthy ecosystem. J Nucl Med, 2023; 64 (2) 188-196.

Song T-A, Malekzadeh M, Saxena R, Purcell SM, Dutta J. A transformer model for predicting human cognition from sleep. bioRxiv 2022.07.17.500351. [Preprint]. July 17, 2022.

Bradshaw T, Boellaard R, Dutta J, Jha A, Jacobs P, Li Q, Liu C, Sitek A, Saboury B, Scott P, Slomka P, Sunderland J, Wahl R, Yousefirizi F, Zuehlsdorff S, Rahmim A, Buvat I. Nuclear medicine and artificial intelligence: Best practices for algorithm development. J Nucl Med, 2022; 63 (4) 500-510.

Song T-A, Yang F, Dutta J. Noise2Void: Unsupervised denoising of PET images. Phys Med Biol, 2021; 66:214002.

Yang F, Chowdhury SR, Jacobs HIL, Sepulcre J, Wedeen VJ, Johnson KA, Dutta J. Longitudinal predictive modeling of tau progression along the structural connectome. NeuroImage, 2021; 237: 118126.

Song T-A, Chowdhury SR, Yang F, Dutta J. PET image super-resolution using generative adversarial networks. Neural Netw. 2020 May;125: 83-91.

Song T-A, Chowdhury SR, Yang F, Dutta J. Super-resolution PET imaging using convolutional neural networks. IEEE Trans Comput Imaging. 2020 Jan;6: 518-28.

Song T-A, Chowdhury SR, Yang F, Sepulcre J, Jacobs HIL, Wedeen V, Johnson KA, Dutta J. A physics-informed geometric learning model for pathological tau spread in Alzheimer's disease. Medical Image Computing and Computer Assisted Intervention (MICCAI), Lima, Peru, Oct 4-8, 2020.

Song T-A, Yang F, Chowdhury SR, Kim K, Johnson KA, El Fakhri G, Li Q, Dutta J. PET image deblurring and super-resolution with an MR-based joint entropy prior. IEEE Trans Comput Imaging. 2019 Dec;5(4): 530-9.

Joyita Dutta

Institute for Applied Life Sciences