Sayantan Bhadra

Sayantan Bhadra

Postdoctoral Fellow at NIH Clinical Center

I am a Postdoctoral Fellow in Radiology and Imaging Sciences at the National Institutes of Health (NIH) Clinical Center, supervised by Dr. Ronald Summers. My research focuses on developing and assessing novel deep learning methods to advance computer-aided diagnosis. I earned my Ph.D. degree in Computer Science and Engineering from Washington University in St. Louis in 2023, advised by Dr. Mark Anastasio. My doctoral dissertation was on the topic of improving image reconstruction using deep generative models and guided by principles of image formation. Before joining my Ph.D program, I completed my B.E. degree in Electronics and Telecommunication Engineering from Jadavpur University in 2016.

News

  • Paper on finding multiple data-consistent solutions of ill-posed tomographic imaging problems with a style-based GAN available on arXiv 2022 (preprint)
  • Paper on learning stochastic object models with advanced AmbientGANs published in SPIE Journal of Medical Imaging 2022 (paper)
  • Research on hallucinations in medical imaging highlighted in IEEE Spectrum: Medical Image AIs Need a Good “Hallucination Map”
  • Featured in research news by the Beckman Institute: Investigating medical imaging hallucinations
  • Paper defining hallucinations in ill-posed imaging inverse problems published in IEEE Transactions on Medical Imaging 2021 under the Second Special Issue on Machine Learning for Image Reconstruction (paper)
  • Paper on improved generative-model constrained image reconstruction with invertible neural networks published in IEEE Transactions on Computational Imaging 2021 (paper)

Research

  • Mining the manifolds of deep generative models for multiple data-consistent solutions of ill-posed tomographic imaging problems
    arXiv (2022)
    Sayantan Bhadra, Umberto Villa, Mark A. Anastasio
    [preprint] [code]

  • Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
    Journal of Medical Imaging (2022)
    Weimin Zhou, Sayantan Bhadra, Frank J. Brooks, Hua Li, Mark A. Anastasio
    [paper] [project]

  • On hallucinations in tomographic image reconstruction
    IEEE Transactions on Medical Imaging (2021)
    Sayantan Bhadra, Varun A. Kelkar, Frank J. Brooks, Mark A. Anastasio
    [paper] [code] [project]

  • Compressible latent-space invertible networks for generative model-constrained image reconstruction
    IEEE Transactions on Computational Imaging (2021)
    Varun A. Kelkar, Sayantan Bhadra, Mark A. Anastasio
    [paper] [project]

  • Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networks
    SPIE Medical Imaging (2020)
    Sayantan Bhadra, Weimin Zhou, Mark A. Anastasio
    [proceeding] [project]

  • Full-view 3D imaging system for functional and anatomical screening of the breast
    SPIE Photonics West BiOS (2018)
    (with TomoWave Laboratories and MD Anderson Cancer Center)
    A. Oraevsky, R. Su, H. Nguyen, J. Moore, Y. Lou, S. Bhadra, L. Forte, M.A. Anastasio, W. Yang
    [proceeding]

  • Real-time low-field cardiac MRI using an integrated MRI-guided radiotherapy system
    ISMRM (2018)
    (with WashU Radiation Oncology and ViewRay)
    H.M. Gach, S. Bhadra, A.N. Curcuru, R. Nana, C.G. Robinson, P.S. Cuculich, S. Mutic, M.A. Anastasio
    [proceeding]