Deep learning cancer radiology to predict immunotherapy response
Deep learning is part of a broader family of machine learning methods based on Artificial Intelligence. In cancer radiology, it enables the non-invasive characterisation of the radiomic phenotype of the entire tumour. Although proof-of-principle associations between radiomics data and treatment response have been established, further investigations into the clinical value of radiomic data are warranted. The EU-funded CANCER-RADIOMICS project will analyse multicentre clinical data, including non-invasive imaging, clinical outcomes and extensive biologic characterisation of patients with lung or melanoma cancer. The aim of the project is to develop deep learning radiomic biomarkers to predict treatment response based on imaging analysis. It will also investigate whether radiomics can improve response prediction and assist patient selection for cancer therapies.
Fields of science
Call for proposal
See other projects for this call