Radiomics: Current Challenges in Clinical Validation

Radiomics can be defined as the extraction and analysis of large amounts of advanced quantitative imaging features with high throughput from medical images obtained with various modalities [1]. Radiomics methods can be applied across various cancers to identify tumor phenotype characteristics in the images that correlate with their likelihood of survival, as well as their association with the underlying driving biology. Identifying this characteristic set of features called tumor signature, holds tremendous value in predicting cancer behavior and progression, which in turn has the potential to predict cancer’s response to various therapeutic options. In allowing us to have this capacity, radiomics holds the promise of driving the engine of precision medicine. However, there are numerous challenges in the validation methods needed to establish it as a clinically viable solution.