Current status of Radiomics for cancer management: Challenges versus opportunities for clinical practice

摘要

Radiomics, the high‐throughput extraction and analysis of featuresfrom medical images, is a promising field for characterizing tumorphenotype and normal tissue injury post‐radiotherapy. Radiomicsprovides unique opportunities to identify predictive and prognosticimaging biomarkers in noninvasive imaging assays providing so‐called digital biopsies that can be acquired throughout the wholecourse of cancer treatment. Radiomics have been proved to beassociated with underlying gene expression and therapy response,which is an area currently referred to as radiogenomics. Multimodalityimaging biomarkers extracted from positron emissiontomography (PET), computed tomography (CT), magnetic resonanceimaging (MRI), and images in other medical modalities have beenshown to have discriminative power for cancer treatment outcomeprognosis and prediction. For example, F‐fluoro‐2‐deoxy‐D‐glucose(FDG)‐PET images are the standard of care in tumor quantificationof head and neck radiation therapy (RT) and will likely remain sofor the foreseeable future. Metabolic tumor volume, defined as thevolume of tumor tissues with increase and heterogeneous FDGuptakes, is an important prognostic factor in many malignancies.The radiomics features can complement known first order imagingbiomarkers and provide further insights beyond those revealed tonaked eyes from medical images.