Premium
SU‐F‐R‐24: Identifying Prognostic Imaging Biomarkers in Early Stage Lung Cancer Using Radiomics
Author(s) -
Zeng X,
Wu J,
Cui Y,
Gao H,
Li R
Publication year - 2016
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4955796
Subject(s) - medicine , hazard ratio , proportional hazards model , stage (stratigraphy) , lung cancer , retrospective cohort study , cancer , radiomics , radiology , institutional review board , oncology , concordance , imaging biomarker , confidence interval , magnetic resonance imaging , surgery , paleontology , biology
Purpose: Patients diagnosed with early stage lung cancer have favorable outcomes when treated with surgery or stereotactic radiotherapy. However, a significant proportion (∼20%) of patients will develop metastatic disease and eventually die of the disease. The purpose of this work is to identify quantitative imaging biomarkers from CT for predicting overall survival in early stage lung cancer. Methods: In this institutional review board‐approved HIPPA‐compliant retrospective study, we retrospectively analyzed the diagnostic CT scans of 110 patients with early stage lung cancer. Data from 70 patients were used for training/discovery purposes, while those of remaining 40 patients were used for independent validation. We extracted 191 radiomic features, including statistical, histogram, morphological, and texture features. Cox proportional hazard regression model, coupled with the least absolute shrinkage and selection operator (LASSO), was used to predict overall survival based on the radiomic features. Results: The optimal prognostic model included three image features from the Law's feature and wavelet texture. In the discovery cohort, this model achieved a concordance index or CI=0.67, and it separated the low‐risk from high‐risk groups in predicting overall survival (hazard ratio=2.72, log‐rank p=0.007). In the independent validation cohort, this radiomic signature achieved a CI=0.62, and significantly stratified the low‐risk and high‐risk groups in terms of overall survival (hazard ratio=2.20, log‐rank p=0.042). Conclusion: We identified CT imaging characteristics associated with overall survival in early stage lung cancer. If prospectively validated, this could potentially help identify high‐risk patients who might benefit from adjuvant systemic therapy.