website picture

PhD Candidate
Harvard-MIT Program in Health Sciences and Technology

Group: Computer Science and Artificial Intelligence Laboratory
Advisor: Dr. Polina Golland

I am a third-year PhD candidate at MIT CSAIL advised by Dr. Polina Golland. Motivated by unmet clinical needs, my research develops biomedical machine learning methods that deepen our ability to understand and treat diseases (Google Scholar).


Differentiable Rendering + Surgery


Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering

Vivek Gopalakrishnan, Neel Dey, Polina Golland

arXiv, 2023

We use X-ray renderering to develop DiffPose, a self-supervised framework for differentiable 2D/3D image registration that achieves sub-millimeter registration accuracy.


Machine Learning for Automated and Real-Time 2D/3D Registration of the Spine using a Single Radiograph

Andrew Abumoussa, Vivek Gopalakrishnan, Benjamin Succop, Michael Galgano, Sivakumar Jaikumar, Yeuh Z. Lee, Deb A. Bhowmick

Neurosurgical Focus, 2023

We use DiffDRR to solve a 2D/3D registration problem in image-guided spinal surgery.


Fast Auto-Differentiable Digitally Reconstructed Radiographs for Solving Inverse Problems in Intraoperative Imaging

Vivek Gopalakrishnan, Polina Golland

MICCAI Clinical Image-based Procedures Workshop, 2022

We present DiffDRR, a differentiable X-ray renderer that can be used to solve inverse problems in X-ray imaging with deep learning (e.g., registration or reconstruction).

Drug Discovery


Learning Interpretable Single-Cell Morphological Profiles from 3D Cell Painting Images

Vivek Gopalakrishnan, Jingzhe Ma, Zhiyong Xie

Society of Biomolecular Imaging and Informatics, 2023 (President's Innovation Award)

Supervised deep learning models are used ubiquitiously throughout image-based drug discovery. We discover a mechanism by which these models cheat and propose an interpretability metric to quantify the level of confounding.

Statistical Graph Theory

corpus callosum

Multiscale Comparative Connectomics

Vivek Gopalakrishnan, Jaewon Chung, Eric Bridgeford, Benjamin D. Pedigo, Jesús Arroyo, Lucy Upchurch, G. Allan Johnson, Nian Wang, Carey E. Priebe, Joushua T. Vogelstein

arXiv, 2021

We introduce a set of multiscale hypothesis tests to facilitate the robust and reproducible discovery of hierarchical brain structures that vary in relation with phenotypic profiles.

ASE clustering

Statistical Connectomics

Jaewon Chung, Eric Bridgeford, Jesús Arroyo, Benjamin D. Pedigo, Ali Saad-Eldin, Vivek Gopalakrishnan, Ling Xiang, Carey E. Priebe, Joushua T. Vogelstein

Annual Review of Statistics and Its Application, 2021

From a statistical graph theory perspective, we review models, assumptions, problems, and applications that are theoretically and empirically justified for analysis of connectome data.