Discovery Radiomics for Computed Tomography Cancer Detection

Lung cancer is one of the most diagnosed form of cancer in the world and the leading cause for cancer related deaths. A powerful tool that can aid radiologists in delivering more accurate and faster diagnosis is radiomics, where a wealth of quantitative imaging features are derived from imaging data for characterizing tumour phenotype and for quantitative diagnosis. In this study, we take the idea of radiomics one step further by introducing the concept of discovery radiomics for lung cancer detection using CT imaging data. Rather than using pre-defined, hand-engineered feature models as with current radiomics-driven methods, we discover custom radiomic sequencers that can generate radiomic sequences consisting of abstract imaging-based features tailored for characterizing lung tumour phenotype. In this study, we realize these custom radiomic sequencers as deep convolutional sequencers, and discover such sequencers using a deep convolutional neural network learning architecture directly based on a wealth of CT imaging data. To illustrate the prognostic power and effectiveness of the radiomic sequences produced by the discovered sequencer, we perform a classification between malignant and benign lung lesions using helical lung CT scans captured from 93 patients with diagnostic data from the LIDC-IDRI dataset. Using the clinically provided diagnostic data as ground truth, classification using the discovered radiomic sequencer provided an average accuracy of 77.52% via 10-fold cross-validation with a sensitivity of 79.06% and specificity of 76.11%. These results illustrate the potential for the proposed discovery radiomics approach in aiding radiologists in improving screening efficiency and accuracy.