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).

Public Health Relevance

Non-small cell lung cancer (NSCLC) is the leading cause of cancer deaths worldwide and hence, even incremental improvements in the care and treatment of these patients can have a profound impact. Virtually all NSCLC patients receive high-quality diagnostic CT imaging studies to assess extent of disease. The work in the current proposal will analyze these images more deeply than the current standard, and use this 'radiomic' information to help oncologists and patients make a better informed decision whether or not to treat post- surgery with adjuvant chemotherapy (AT). This decision is of profound significance, because, although AT can prevent recurrence, it can also cause significant morbidities and even death.

National Institute of Health (NIH)
National Cancer Institute (NCI)
Research Project--Cooperative Agreements (U01)
Project #
Application #
Study Section
Special Emphasis Panel (ZCA1-TCRB-W (J1))
Program Officer
Tata, Darayash B
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
H. Lee Moffitt Cancer Center & Research Institute
United States
Zip Code
Cherezov, Dmitry; Hawkins, Samuel H; Goldgof, Dmitry B et al. (2018) Delta radiomic features improve prediction for lung cancer incidence: A nested case-control analysis of the National Lung Screening Trial. Cancer Med 7:6340-6356
Paul, Rahul; Liu, Ying; Li, Qian et al. (2018) Representation of Deep Features using Radiologist defined Semantic Features. Proc Int Jt Conf Neural Netw 2018:
Napel, Sandy; Mu, Wei; Jardim-Perassi, Bruna V et al. (2018) Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats. Cancer 124:4633-4649
Liu, Ying; Wang, Hua; Li, Qian et al. (2018) Radiologic Features of Small Pulmonary Nodules and Lung Cancer Risk in the National Lung Screening Trial: A Nested Case-Control Study. Radiology 286:298-306
Alahmari, Saeed S; Cherezov, Dmitry; Goldgof, Dmitry et al. (2018) Delta Radiomics Improves Pulmonary Nodule Malignancy Prediction in Lung Cancer Screening. IEEE Access 6:77796-77806
Paul, Rahul; Hall, Lawrence; Goldgof, Dmitry et al. (2018) Predicting Nodule Malignancy using a CNN Ensemble Approach. Proc Int Jt Conf Neural Netw 2018:
Liu, Ying; Kim, Jongphil; Balagurunathan, Yoganand et al. (2018) Prediction of pathological nodal involvement by CT-based Radiomic features of the primary tumor in patients with clinically node-negative peripheral lung adenocarcinomas. Med Phys 45:2518-2526
Balagurunathan, Yoganand; Beers, Andrew; Kalpathy-Cramer, Jayashree et al. (2018) Semi-automated pulmonary nodule interval segmentation using the NLST data. Med Phys 45:1093-1107
Li, Qian; Balagurunathan, Yoganand; Liu, Ying et al. (2018) Comparison Between Radiological Semantic Features and Lung-RADS in Predicting Malignancy of Screen-Detected Lung Nodules in the National Lung Screening Trial. Clin Lung Cancer 19:148-156.e3
Paul, Rahul; Hawkins, Samuel H; Schabath, Matthew B et al. (2018) Predicting malignant nodules by fusing deep features with classical radiomics features. J Med Imaging (Bellingham) 5:011021

Showing the most recent 10 out of 85 publications