My main research areas are the development of novel MR and MR-PET methods including data acquisition, image reconstruction and multimodality data analysis, and application of machine learning in the medical imaging domain. I am also active in translating fundamental medical imaging development and scientific discoveries into real-world applications.
I am affiliated with the following organisations:
I am an ISMRM annual meeting committee member (2018-2021).
I am a member of the following societies: (i) IEEE EMBC, (ii) Society for Neuroscience, (iii) SNMMI, (iv) MICCAI.
Review Editor for Frontiers of Neuroscience.
Academic Editor for PLoS One
I review for a broad range of journals in biomedical imaging and image processing, and review for competitive grant schemes.
Two new PhD scholarship opportunity !! [link]
My MBI Webinar on Machine learning for biomedical image reconstruction. [link]
Succesful ARC DP project on Biophysics-informed deep learning framework for magnetic resonance imaging (# DP210101863) !!
Great to be part of this successful grant - ARDC, Australian Cancer Data Network: distributed learning from clinical data.
Below are some examples and related tweets
MoCoNET:deep learning motion correction
Pawar K. et al. (2020) Suppressing Motion Artefacts in MRI using an Inception-Resnet Network with Motion Simulation Augmentation, NMR in Biomed. https://doi.org/10.1002/nbm.4225.
Pawar K. et al. (2020) Clinical Utility of Deep Learning Motion Correction for T1 weighted MPRAGE MR Images. European Journal of Radiology. 10.1016/j.ejrad.2020.109384
Pixel Classification for image reconstruction
Multimodal functional MRI and PET Analysis model
Joint MRI and PET image reconstruction
Sudarshan, P.S. et al (2020) Joint MRI-PET image reconstruction using a joint dictionary, Medical Imaging Analysis. https://doi.org/10.1016/j.media.2020.101669
Sudarshan, P.S. et al (2018) Joint PET+MRI Patch-based Dictionary for Bayesian Random Field PET Reconstruction, 2018 International conference on medical image computing and Computer Assisted Intervention (MICCAI), Granada, September 16-20, 2018.
Deep learning MR-PET attenuation correction
Pozaruk, A. et al (2020) augmented deep learning model for improved quantitative accuracy of MR based PET attenuation correction in prostate cancer, European Journal of Nuclear Medicine and Molecular Imaging (EJNMMI). https://doi.org/10.1007/s00259-020-04816-9.