Click here to

Session: Advances in Automatic Segmentation, Treatment Planning and QA [Return to Session]

Advances in Automatic Segmentation, Treatment Planning and QA

H Veeraraghavan1*, Q Wu2*, E Ford3*, S Jiang4*, (1) Memorial Sloan Kettering Cancer Center, New York, NY, (2) Duke University Medical Center, Durham, NC, (3) University of Washington, Seattle, WA, (4) UT Southwestern Medical Center, Dallas, TX

Presentations

1:00 PM Deep Learning Automated Segmentation for Radiation Therapy Planning - H Veeraraghavan, Presenting Author
1:30 PM Automation in Treatment Planning Process - Q Wu, Presenting Author
2:00 PM Advances in Quality Assurance Through Automation - E Ford, Presenting Author
2:30 PM Thoughts on The Clinical Implementation of AI Tools In Treatment Planning Process - S Jiang, Presenting Author

SU-CD-TRACK 5-0 (Sunday, 7/25/2021) 1:00 PM - 3:00 PM [Eastern Time (GMT-4)]

Recent advances in segmentation, planning, and QA are largely enabled by innovative applications of artificial intelligence (AI) techniques. AI refers to methods that improve and automate challenging human tasks by systematically capturing and applying relevant knowledge in these tasks.

Over the past decades, a number of AI approaches have been developed to address different needs of system intelligence in treatment planning, ranging from search strategies to knowledge representation to machine learning. In particular, deep learning techniques have found tremendous success in the segmentation of normal anatomical structures as well as treatment target volumes; and also have shown great promise in accurately predicting dose distributions and fluence maps resulting in completely automated algorithms for generating treatment plans with clinically viable qualities. Robust systems that integrate multiple AI and machine learning algorithms have also been developed to automate entire clinical workflows in radiation therapy. Moreover, quality assurance has also benefited significantly from recent advances. Data-driven intelligent algorithms are making the QA process more efficient and effective.

This session presents recent developments of AI algorithms and other novel approaches to improving segmentation, planning, and QA in the treatment planning process; and discusses the potential changes of clinical workflow these technologies may bring.

The learning objectives:
1. Understand current AI techniques and algorithms that have been developed for segmentation, planning and quality assurance
2. Understand the issues related to developing AI tools in these targeted applications
3. Understand potential challenges in implementing and integrating these techniques in clinical workflow and preparations for adoption

Funding Support, Disclosures, and Conflict of Interest: NIH R01CA201212 Varian Medical System Master Research Agreement

Keywords

Treatment Planning, Treatment Verification, Segmentation

Taxonomy

Not Applicable / None Entered.

Contact Email

Share: