BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:98@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20250113T140000
DTEND;TZID=Asia/Kolkata:20250113T150000
DTSTAMP:20250110T121225Z
URL:https://cds.iisc.ac.in/events/seminar-cds-102-january-13th-1400-comput
 er-vision-in-the-operating-room-differentiable-x-ray-rendering-for-intraop
 erative-inverse-problems/
SUMMARY:{Seminar} @ CDS: #102\, January 13th\, 14:00: "Computer Vision in t
 he Operating Room: Differentiable X-ray Rendering for Intraoperative Inver
 se Problems"
DESCRIPTION:Department of Computational and Data Sciences\nDepartment Semin
 ar\n\n\n\nSpeaker : Mr. Vivek Gopalakrishnan\, Ph.D. Student @ MIT\nTitle 
 : "Computer Vision in the Operating Room: Differentiable X-ray Rendering f
 or Intraoperative Inverse Problems"\nDate &amp\; Time : January 13\, 2025 
 (Monday)\, 02:00 PM\nVenue : # 102\, CDS Seminar Hall\n\n\n\nABSTRACT\nHum
 ans possess the innate ability to perceive the 3D geometry of scenes in na
 tural images\, inspiring numerous attempts in computer vision to build mac
 hines capable of doing the same. However\, for medical images\, the comple
 xity of human anatomy\, combined with optical properties inherent to medic
 al imaging systems\, limits the accuracy of our mental reconstructions (e.
 g.\, the penetrating radiation used in X-rays makes it impossible to deter
 mine which objects occlude others from imaging alone). In this talk\, I wi
 ll demonstrate how differentiable implementations of the X-ray image forma
 tion model can power self-supervised solutions to inverse problems in intr
 aoperative settings. Our key contributions include (A) DiffPose\, a framew
 ork for training patient-specific 2D/3D X-ray to CT registration networks 
 that achieve\, for the first time\, consistent submillimeter accuracy and 
 (B) DiffVox\, a 3D CBCT reconstruction method that achieves state-of-the-a
 rt 3D reconstructions from sparse numbers of posed X-ray images. Finally\,
  I will briefly demonstrate algorithmic advancements towards making these 
 computer vision methods surgically deployable.\n\n 	DiffDRR (rendering): h
 ttps://github.com/eigenvivek/DiffDRR\n 	DiffPose (registration): https://a
 rxiv.org/abs/2312.06358\n 	DiffVox (reconstruction): https://arxiv.org/abs
 /2411.19224\n\nBIO: Vivek is a PhD student in Medical Engineering and Medi
 cal Physics at the Harvard-MIT Program in Health Sciences and Technology\,
  advised by Polina Golland. The goal of his research is to address unmet c
 linical needs through the development of biomedical machine learning metho
 ds that deepen our ability to understand and treat disease. Vivek's curren
 t focus is on developing scalable synthetic data generation strategies to 
 solve challenging 3D computer vision problems in diagnostic and interventi
 onal radiology. More details: https://vivekg.dev/\n\nHost Faculty: Prof. P
 haneendra Yalavarthy\n\n\n\nALL ARE WELCOME
CATEGORIES:Events,Talks
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20240114T140000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR