BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Segment Anything in Medical Images - Dr Bo Wang\, University of To
 ronto and Vector Institute of Artificial Intelligence
DTSTART:20230607T120000Z
DTEND:20230607T130000Z
UID:TALK201613@talks.cam.ac.uk
CONTACT:Yuan Huang
DESCRIPTION:Medical imaging plays an indispensable role in clinical practi
 ce. Accurate and efficient medical image segmentation provides a means of 
 delineating regions of interest and quantifying various clinical metrics. 
 However\, building customized segmentation models for each medical imaging
  task can be a daunting and time-consuming process\, limiting the widespre
 ad adoption in clinical practice. In this talk\, I will introduce MedSAM\,
  a segmentation foundation model that enables universal segmentation acros
 s a wide range of medical imaging tasks and modalities. MedSAM achieved re
 markable improvements in 30 segmentation tasks\, surpassing the existing s
 egmentation foundation model by a large margin. MedSAM also demonstrated z
 ero-shot and few-shot capabilities to segment unseen tumor types and adapt
  to new imaging modalities with minimal effort. Our results validate the v
 ersatility of MedSAM compared to existing customized segmentation models\,
  emphasizing its potential to transform medical image segmentation and enh
 ance clinical practice. This work underscores the significance of creating
  adaptable and efficient segmentation tools that can meet the growing dema
 nds of personalized healthcare and contribute to the ongoing progress in m
 edical imaging analysis.\n\nThis seminar will be held online via ZOOM.\n*J
 oin Zoom Meeting:* https://maths-cam-ac-uk.zoom.us/j/93331132587?pwd=MlpRe
 FY3MVpyVThlSi85TmUzdTJxdz09
LOCATION:Virtual (see abstract for Zoom link)
END:VEVENT
END:VCALENDAR