Profile Image

Amar Kumar

Ph.D. Candidate, McGill University

Hi, I am a PhD student working under the supervision of Prof. Tal Arbel in the Probabilistic Vision Group (PVG). My research interest lies in using generative modelling for developing explainable AI (XAI) models.

You can find my complete CV here.

Research Interests

  • Neuroimage Analysis
  • Deep Learning
  • Explainable AI (XAI)
  • Generative Modelling
  • Computer vision


  • Bachelor of Technology (B.Tech)

    Indian Institute of Technology Delhi, Delhi, India

  • mcgill logo mini


    McGill University, Montreal, Canada


  • Senior Research Analyst

    Hedge Fund, India

  • Research Intern

    University of Victoria, Canada

  • Research Intern

    TIFR, India

Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markers

[Accepted to MIABID 2022] The discovery of patient-specific imaging markers that are predictive of future disease outcomes can help us better understand individual-level heterogeneity of disease evolution. In fact, deep learning models that can provide data-driven personalized markers are much more likely to be adopted in medical practice. In this work, we demonstrate that data-driven biomarker discovery can be achieved through a counterfactual synthesis process. We show how a deep conditional generative model can be used to perturb local imaging features in baseline images that are pertinent to subject-specific future disease evolution and result in a counterfactual image that is expected to have a different future outcome. Candidate biomarkers, therefore, result from examining the set of features that are perturbed in this process. Through several experiments on a large-scale, multi-scanner, multi-center multiple sclerosis (MS) clinical trial magnetic resonance imaging (MRI) dataset of relapsing-remitting (RRMS) patients, we demonstrate that our model produces counterfactuals with changes in imaging features that reflect established clinical markers predictive of future MRI lesional activity at the population level. Additional qualitative results illustrate that our model has the potential to discover novel and subject-specific predictive markers of future activity.

Study image

2021, made with in pure Bootstrap 4, inspired by Academic Template for Hugo