Radiomics as Applied in Precision Medicine

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, including nuclear medicine modalities of Single photon emission computed tomography (SPECT) and Positron emission tomography (PET). We describe it as the process of transferring the medical imaging interpretation knowledge and skill set from humans to machines in a way that they can see more, process more information, and have deeper insights into what the disease is and how it behaves and might respond to therapeutic intervention. 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 (Fig. 3.1). Moreover, we are beginning to see the application of radiomics principles in non-oncologic indications as well, such as cardiovascular disease. 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 radiomics as a clinically viable solution.