Sign Up

Physics Department Open Seminar:  Dr. Christina Sarosiek '16 

This is a past event.

Tuesday, November 29, 2022 11am

27 Graves Place, Holland, MI 49423-3617

A Deep learning-based Automatic Contour Refinement Method  for MRI-guided Online Adaptive Radiotherapy  
Radiation therapy is a cancer treatment that uses radiation to kill cancer  cells and reduce tumor size. The radiation treatment plans rely on  computed tomographic (CT) images of the patient taken prior to the first treatment day to accurately predict the dose delivered to the patient. However, daily changes in anatomy such as weight loss/gain or  tumor shrinkage can reduce the accuracy of these treatment plans and lead to underdosing the tumor or overdosing healthy tissues. MRI guidance in radiotherapy allows for more frequent imaging without excess dose to the patient and has an additional benefit of improved  soft tissue visualization in the abdomen. Online adaptive radiotherapy  (OART) uses recent advances in artificial intelligence to quickly adapt  the original treatment plan to the anatomy of the day. One major  piece of the OART process involves creating new anatomical contours  on the daily MR image. Deep learning-based automatic segmentation  methods do not produce quality contours sufficient for treatment and  require manual correction. Our group is developing an automated contour refinement workflow to improve contours after initial automatic  segmentation with the overall goal to make MRI-guided radiotherapy  treatments safer, more efficient, and more effective. 

(Left) Example slice from an abdominal MRI taken with an MR-linac  at MCW. (Right) Same MR slice cropped in to show the stomach.  The blue contour was drawn manually by a physicist for treatment  planning. In OART, the auto-segmentation method produces in correct contours, such as the one shown in green. We can use deep  learning to improve the accuracy of the incorrect contours. The red  corrected contour shows good agreement with that of the manually  drawn contour in blue  and thus can be used  for treatment planning.  

Christina Sarosiek (Hope College ’16) is a post-doctoral fellow at the Medical College of Wisconsin. She  received her PhD in Physics in 2021 from Northern Illinois University where she studied the clinical  applications of proton computed tomography and proton radiography. She is now applying deep learning  to online adaptive radiotherapy by developing techniques to automatically correct anatomical contours. ;
Meet Dr. Sarosiek in this short interview-^ 

Event Details

0 people are interested in this event

User Activity

No recent activity

Hope College Calendar Powered by the Localist Community Event Platform © All rights reserved