Radiology’s Evolving Role in Precision MedicineRSNA - by Paul LaTour
"Radiology can assuage the physicians’ concerns by harnessing big data with imaging radiomics to create predictive models, said Maryellen Giger, PhD, also a symposium presenter.
Creating predictive models involves receiving input from clinical data (including environmental data), radiology data, pathology data, protein data and gene testing data. But, as Dr. Giger points out, that is a lot of data to harness.
'It’s basically information overload,' said Dr. Giger, A.N. Pritzker Professor of Radiology, the Committee on Medical Physics and the College at the University of Chicago.
From a research perspective, Dr. Giger said a two-stage process is required to prevent overload — discovery and application.
The discovery stage involves looking at imaging data and the various ‘-omic’ data (radiomics, pathomics, proteomics, genomics) to discover their relationship with each other. This stage is a multidisciplinary data-mining effort involving radiologists, medical physicists, statisticians, oncologists, computer scientists and other researchers.
Dr. Giger compared this to the way the genomics community approached the Cancer Genome Project.
'The radiologic community needs to continue to conduct robust collection, annotation, analysis and evaluation of images of large populations,' she said."