MIT Building 32-D463
32 Vassar Street, Cambridge, MA 02139
Estimating 3D Structure and Dynamics from 2D Intraoperative Imaging
Humans possess the innate ability to perceive the three-dimensional (3D) geometry and motion in natural images, inspiring numerous attempts in computer vision to build machines capable of doing the same. However, in medical images, the complexity of human anatomy, combined with physical properties inherent to medical imaging systems, limits the accuracy of our mental reconstructions. For example, the penetrating radiation used in two-dimensional (2D) X-rays makes it impossible to determine which objects occlude others from imaging alone. Nowhere are these perceptual challenges more consequential than in minimally invasive image-guided procedures, where clinicians rely on live 2D X-ray video to navigate and deploy surgical devices within complex 3D anatomy at millimeter-level precision. This thesis proposes a unified framework for recovering real-time 3D information by registering a patient's preoperative volume (CT or MRI) to their intraoperative 2D images. The framework simulates the physics of image formation to construct patient-specific models, which are aligned to live imaging through gradient-based optimization. Within this framework, we develop algorithms that recover the imaging geometry, anatomical pose, and non-rigid motion that relate a 2D image to the underlying 3D scene, solving clinical problems across interventional radiology, radiation oncology, and surgical robotics.
Thesis Supervisor:
Polina Golland, PhD
Sunlin (1966) and Priscilla Chou Professor of Electrical Engineering and Computer Science, MIT
Thesis Committee Chair:
Collin Stultz, PhD, MD
Nina T. and Robert H. Rubin Professor, Electrical Engineering & Computer Science and Institute for Medical Engineering & Science, MIT
Thesis Reader:
Vincent Sitzmann, PhD
Associate Professor of Electrical Engineering and Computer Science, MIT
________________________________________________________________________________________
Zoom Invitation
Vivek Gopalakrishnan is inviting you to a scheduled Zoom meeting
Topic: Vivek Gopalakrishnan MEMP PhD Thesis Defense
Time: Friday, July 10, 2026, 2:00 PM Eastern Time (US and Canada)
Your participation is important to us: please notify hst [at] mit.edu (hst[at]mit[dot]edu), at least 3 business days in advance, if you require accommodations in order to access this event.
Join Zoom Meeting
https://mit.zoom.us/j/99182066099
One tap mobile
+16465588656,,99182066099# US (New York)
+16699006833,,99182066099# US (San Jose)
Meeting ID: 991 8206 6099
US: +1 646 558 8656 or +1 669 900 6833
International Numbers: https://mit.zoom.us/u/aejeJIPgZK
Join by SIP
99182066099 [at] zoomcrc.com (99182066099[at]zoomcrc[dot]com)
Join by Skype for Business
https://mit.zoom.us/skype/99182066099