Computational Imaging

Co-designing acquisition hardware and reconstruction algorithms with learning.

Imaging systems infer anatomy and tissue properties from indirect measurements, yet acquisition and reconstruction have usually been designed separately. My work treats them as one learnable system, from ultrasound beamforming to MRI sampling trajectories and radar. The goal is to measure only what a clinical or scientific question needs. Current work extends this toward quantitative ultrasound tomography.

Selected work

* Equally-contributing first author, † Equally-contributing senior author

2026

  1. IUS
    IUS2026
    View-wise spatially-varying Richardson-Lucy (RL) deconvolution for refraction-corrected 3D ultrasound reflection tomography
    J. Wiskin, S. Vedula, B. Malik, M. Magno, A. Bronstein
    Proc. IEEE International Ultrasonics Symposium (IUS)
  2. IUS
    IUS2026
    Comparison of three methods for deconvolution for refraction-corrected 3D ultrasound reflection tomography
    J. Wiskin, S. Vedula, B. Malik, M. Magno, A. Bronstein
    Proc. IEEE International Ultrasonics Symposium (IUS)

2021

  1. weiss2021joint.png
    MLSP2021
    Joint optimization of system design and reconstruction in MIMO radar imaging
    T. Weiss, N. Peretz, S. Vedula, A. Feuer, A. Bronstein
    2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)
  2. weiss2021pilot.png
    MELBA2021
    PILOT: Physics-informed learned optimal trajectories for accelerated MRI
    T. Weiss, O. Senouf, S. Vedula, O. Michailovich, M. Zibulevsky, A. Bronstein
    The Journal of Machine Learning for Biomedical Imaging
    HTML

2020

  1. weiss2020towards.png
    CDMRI2020
    Towards learned optimal q-space sampling in diffusion MRI
    T. Weiss, S. Vedula, O. Senouf, O. Michailovich, A. Bronstein
    Computational Diffusion MRI
  2. alush20203d.png
    MICCAI-W2020
    3D FLAT-Feasible Learned Acquisition Trajectories for Accelerated MRI
    J. Alush-Aben, L. Ackerman, T. Weiss, S. Vedula, O. Senouf, A. Bronstein
    International Workshop on Machine Learning for Medical Image Reconstruction, MICCAI
  3. weiss2019joint.png
    ICASSP2020
    Joint learning of Cartesian undersampling and reconstruction for accelerated MRI
    T. Weiss, S. Vedula, O. Senouf, A. Bronstein, O. Michailovich, M. Zibulevsky
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

2019

  1. senouf2019self.png
    MICCAI-W2019
    Self-supervised learning of inverse problem solvers in medical imaging
    O. Senouf*, S. Vedula*, T. Weiss, A. Bronstein, O. Michailovich, M. Zibulevsky
    Domain adaptation and representation transfer and medical image learning with less labels and imperfect data, MICCAI
  2. vedula2018learning.png
    MIDL2019
    Learning beamforming in ultrasound imaging
    S. Vedula*, O. Senouf*, G. Zurakhov, A. Bronstein, O. Michailovich, M. Zibulevsky
    Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning (MIDL)
    PDF

2018

  1. senouf2018high.png
    MICCAI2018
    High frame-rate cardiac ultrasound imaging with deep learning
    O. Senouf, S. Vedula, G. Zurakhov, A. Bronstein, M. Zibulevsky, O. Michailovich, D. Adam, D. Blondheim
    International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
  2. vedula2018high.png
    MICCAI-W2018
    High quality ultrasonic multi-line transmission through deep learning
    S. Vedula, O. Senouf, G. Zurakhov, A. Bronstein, M. Zibulevsky, O. Michailovich, D. Adam, D. Gaitini
    International Workshop on Machine Learning for Medical Image Reconstruction, MICCAI

2017

  1. vedula2017towards.png
    arXiv2017
    Towards CT-quality ultrasound imaging using deep learning
    S. Vedula*, O. Senouf*, A. Bronstein, O. Michailovich, M. Zibulevsky
    arXiv preprint arXiv:1710.06304

← All research areas