About Cancer Radiomics

Mission

Cancer Radiomics is a project support by the European Union to improve cancer treatments. Artificial Intelligence (AI) algorithms, deep learning in particular, have demonstrated remarkable progress in the medical imaging field. AI methods excel in automatically recognizing complex patterns in imaging data and can provide quantitative, rather than qualitative, assessments of radiographic characteristics. These AI-powered radiographic biomarkers (“radiomics”) may contribute additional non-invasive information of the cancer phenotype that is clinically actionable, and may further improve cancer diagnosis, characterization, and longitudinal tracking after therapy.

This is particularly important for cancer patients, where different cancer lesions can express different microenvironments that could ultimately lead to heterogeneous response patterns. Despite the remarkable success of novel cancer therapies, the clinical benefit remains limited to a subset and there is a direct need to better identify beneficial patients. Radiomics biomarkers could provide this information on a lesion and patient level using standard- of-care CT scans. Unlike biopsy assays that - by definition - only represent a sample within the tumour, imaging can depict a full picture of the entire tumour burden, providing information of each cancer lesion within a single non-invasive examination.

Goals

The overall goal of this project is to investigate if radiomics can improving cancer characterization and therapy response predictions. Using extensive multicentre data we will develop and validate deep-learning radiomic biomarkers to improve outcome predictions before and after treatment. This project combines several lines of expertise in oncology, radiology, deep-learning, and biostatistics, and brings together scientists from Europe and the United States.