“Radiomics” is the process of extracting structured and mineable data from biomedical images, and then using these data to provide more power for cancer diagnosis and prognosis, as well as prediction and monitoring response to anti-cancer therapies (1). The most well developed area in radiomics is analysis of CT scans from lung cancer patients, which has been the subject of dozens of high impact publications by our group and others (2,3). Through quantitative analyses of lung cancers, predominately non-small cell (NSCLC) adenocarcinoma, radiomics can predict survival, progression, and recurrence with accuracies approaching 90%, and can also define expression of common mutations with accuracies over 80% (4-7).
Robert J Gillies, PhD
PI, Chair of Department