DESCRIPTION (provided by applicant): "Radiomics" is the process of extracting and analyzing mineable, quantitative data from radiographic images. The overarching hypothesis of Radiomics is that image features describing size, shape, and texture reflect underlying tumor pathophysiology and hence, can be developed and qualified as biomarkers for prediction, prognostication or response monitoring. Radiomics is designed to use standard-of-care images, allowing the development and curation of large data sets that are needed for statistical power. In the first cycle of this award, we addressed challenges to all steps in the "radiomic pipeline", viz (1) defining the impact of acquisition and image reconstruction on the quality of radiomics data; (2) curating to maintain high data quality; (3) qualifying semi-automated segmentation tools; (4) statistical qualification of radiomic features; (5) developing database sharing tools to allow rapi hypothesis testing; and (6) developing and applying informatics approaches to these datasets. With this pipeline, we identified and validated specific features from CT images that accurately predicted survival in lung cancer patients treated with surgery or chemo-radiation. In this competing continuation, we intend to build on this prior work to incorporate radiomics into a decision support system for post-surgery management of non-small cell lung cancer (NSCLC) patients. NSCLC is the leading cause of cancer deaths worldwide and hence, even incremental improvements in decision support can have a profound impact on patients' lives. We will use and extend the radiomics framework that we have developed to address a compelling and focused question in lung cancer care: whether to treat post-surgery patients with adjuvant chemotherapy (AT). Virtually all NSCLC surgical candidates receive high-quality diagnostic CTs. Early stage NSCLC patients are commonly resected with lobectomy and mediastinal lymph node removal. Of these, up to 35 percent will experience distant recurrence within 5 years. Recurrence can be reduced with AT, yet the decision whether or not to treat is not trivial, as AT is associated with significant morbidities and even mortality. This decision is currently ill-informed by cancer stage alone. There are no predictive models that can accurately identify which patients have the highest likelihood of recurrence, thus requiring most aggressive adjuvant follow-up. Our proposal will address this important clinical problem by development of a "Risk-of-Recurrence" score with a combination of radiomic, clinical and genomic data curated from over 3,600 patients from two institutions. These data and analytical tools will be shared via unique tools developed for this purpose within the framework of the Quantitative Imaging Network (QIN).