Ballroom C
Precision or personalized medicine has been hailed as a key for improving patient cancer outcomes. It is positioned to provide data-driven insights into improving cancer care and offering actionable treatment options. However, to unlock the potentials of precision medicine, proper application and implementation of artificial intelligence (AI) and machine learning (ML) algorithms are necessary. In this session, the expert panelists will review the common forms of multi-omics with special emphasis on imaging (radiomics) and the different means for feature extraction from multimodality (CT, PET, MR, etc.) images and other omics (genomics, proteomics, etc) in different cancer sites. In addition, the panelists will discuss how to build and validate the robustness of radiomic or multi-omic models for clinical decision support particularly for managing and quantifying tumor response or normal tissue toxicities.
Learning Objectives:
1. Understand the nature of multi-omics data and its value for personalized/precision medicine.
2. Learn about the different challenges in the multi-omics landscape (from imaging radiomics to proteogenomics).
3. Learn about the role of AI/ML in utilizing multi-omics data.
Funding Support, Disclosures, and Conflict of Interest: NIH Funding
Not Applicable / None Entered.
Not Applicable / None Entered.