Click here to


Are you sure ?

Yes, do it No, cancel

Integrating Radiomics and Genomics for Personalized Cancer Therapy in the Era of AI and Big Data

J Wang1*, J Oh2*, J Wu3*, (1) UT Southwestern Medical Center, Dallas, TX, (2) Memorial Sloan-Kettering Cancer Center, Summit, NJ, (3) Stanford University, Palo Alto, CA


(Tuesday, 7/16/2019) 4:30 PM - 6:00 PM

Room: Stars at Night Ballroom 2-3

The fields of radiomics and genomics have garnered significant interest and experienced rapid development and expansion in recent years. This is mainly driven by advances in analytical approaches, increased computing power, and availability of large annotated imaging and genetic data sets in a variety of cancer types. Machine learning and more broadly AI can automatically extract sub-visual features and identify hidden, potentially useful information from complex imaging and genetic data. Indeed, a growing number of studies using radiomics and genomics approaches have shown great promise in various clinical applications.

This symposium will summarize recent advances and present the state of the art on the use of big radiomics and genomics data as well as their integration for a variety of applications, including radiation target identification, treatment response evaluation, radiation toxicity prediction, and prognosis prediction in head and neck cancer, breast cancer, and lung cancer. Through these talks, the audience will understand and appreciate the potential of radiomics and genomics for discovering useful biomarkers to improve clinical decision-making for personalized cancer therapy.

Learning objectives:
1. Learn about recent development on multi-classifier, multi-objective, and multi-modality radiomics models for treatment target identification and outcome prediction.
2. Learn about machine learning-based predictive modeling of radiation-induced toxicities using genome-wide germline single nucleotide polymorphisms (SNPs).
3. Learn about techniques that integrate imaging and genomics data to understand the underlying molecular biology driving the disease phenotypes and improve outcome prediction.

Funding Support, Disclosures, and Conflict of Interest: NIH R01 CA193730, NIH R01 CA222512, NIH R01 CA233578



Not Applicable / None Entered.


Not Applicable / None Entered.

Contact Email