Click here to

  1. Home
  2. Meeting Program
  3. All Sessions
  4. Abstracts
Session: [Return to Session]

AI in Image Guided Radiation Therapy

G Chen1*, L Ren2*, X Yang3*, D Nguyen4*, (1) University of Wisconsin, Madison, WI, (2) University of Maryland, Baltimore, MD, (3) Emory University, Atlanta, GA, (4) University of Technology Sydney, Ultimo, NSW, AU

Presentations

10:30 AM Deep Learning in CT Image Reconstruction - G Chen, Presenting Author
11:00 AM AI Based Image Enhancement: Advances and Clinical Implications - L Ren, Presenting Author
11:30 AM Deep Learning in Image Registration - X Yang, Presenting Author
12:00 PM AI for Intrafraction Motion Monitoring: Are We There Yet? - D Nguyen, Presenting Author

WE-AB-TRACK 4-0 (Wednesday, 7/28/2021) 10:30 AM - 12:30 PM [Eastern Time (GMT-4)]

The progress of artificial intelligence (AI) technologies has recently been exponential and shown to be both transformative and disruptive in many fields, which has impacted many aspects of human life. These AI technologies are now being researched, developed, and applied to healthcare, including radiation therapy. Imaging has become essential not only for the detection and monitoring of disease but also for improving the outcome of radiotherapy. Image-guided radiation therapy (IGRT) uses imaging during radiotherapy to improve the precision and accuracy of treatment delivery. Treatment machines are equipped with imaging technology to image patient anatomy before and during treatment. By comparing these images to the reference images taken during simulation, the patient's position and/or the radiation beams may be adjusted to more precisely deliver the radiation dose to the target. AI-based analytical and computational tools have been developed to enhance the role of quantitative imaging in IGRT and further improve the accuracy and precision of radiotherapy.

In the session, we will focus on the potential impact of AI on four important aspects of IGRT: image reconstruction, image augmentation, image registration, and intrafraction motion monitoring. This session will identify challenges and opportunities of AI, especially deep learning in IGRT, explore strengths and limitations of different AI models in IGRT, outline future trends of AI in IGRT, and highlight specific clinical applications.

Learning Objectives:
1. Learn the challenges in current IGRT and the technologies available or being developed for IGRT.
2. Learn how AI can be utilized to improve current IGRT practice.
3. Identify the rationale, significance, quality, and safety issues of AI in IGRT.
4. Understand the challenges, opportunities, strengths, and limitations of AI in IGRT.

Funding Support, Disclosures, and Conflict of Interest: None.

Keywords

Not Applicable / None Entered.

Taxonomy

Not Applicable / None Entered.

Contact Email

Share:

Additional Links