Click here to

Session: Frontiers in AI and Its Applications in Medical Physics [Return to Session]

Frontiers in AI and Its Applications in Medical Physics

R Zeng1*, T Purdie2*, N Wen3*, L Xing4*, (1) Food & Drug Administration, Rockville, MD, (2) The Princess Margaret Cancer Centre - UHN, Toronto, ON, CA, (3) Henry Ford Health System, Detroit, MI, (4) Stanford University, Stanford, CA


10:30 AM Growing Significance of Deep Learning in Modern Medical Imaging - R Zeng, Presenting Author
11:00 AM Emerging Data-driven Approaches for Treatment Planning - T Purdie, Presenting Author
11:30 AM Unconventional Neural Networks and Their Applications in Cancer Detection and Decision-making - N Wen, Presenting Author
12:00 PM Pitfalls of Current Data-driven Solutions and Pathways Toward XAI for Medical Physics - L Xing, Presenting Author

MO-AB-TRACK 4-0 (Monday, 7/26/2021) 10:30 AM - 12:30 PM [Eastern Time (GMT-4)]

Artificial intelligence driven by deep learning have attracted much attention in the several years and is being increasing adopted in medical physics for various applications. The enormous success of deep learning stems from its unique capabilities of extracting essential features from big data and then making inferences. However, the data-driven process has many potential flaws, such as the demand for a large amount of annotated data and lack of interpretability. The purpose of this symposium is to summarize recent advances in deep learning techniques, in particular, unsupervised and semi-supervised deep learning, graphical neural networks, and technical tools that make AI more interpretable and trustworthy. Specific applications of the new generation of deep learning techniques in imaging, treatment planning, dose delivery, and clinical decision-making will be discussed in detail.

Learning Objectives:
1. Highlighting recent advances in deep learning techniques, such as unsupervised learning and interpretable AI.
2. Presenting new applications of these deep learning algorithms in quantitative imaging, image analysis and treatment planning.
3. Providing a comprehensive overview of the roles of the new generation of neural networks in imaging, treatment planning and therapeutic delivery.

Funding Support, Disclosures, and Conflict of Interest: PI of Master Research Agreement (MRA) with Varian Medical Systems Adviser for More Health Inc., Luca Medical Systems, and Huiyihuiying Med Co.



Not Applicable / None Entered.


Not Applicable / None Entered.

Contact Email