3 years ago

A quantitative CT imaging signature predicts survival and complements established prognosticators in stage I non-small cell lung cancer

Prognostic biomarkers are needed to guide the management of early stage non-small cell lung cancer (NSCLC). This work aims to develop an image-based prognostic signature and assess its complementary value to existing biomarkers. Methods We retrospectively analyzed outcomes of stage I NSCLC in seven cohorts. Based on an analysis of 39 CT features characterizing tumor and its relation to neighboring pleura, we developed a prognostic signature in an institutional cohort (n=117) and tested it in an external cohort (n=88). A third cohort of 89 patients with CT and gene expression data was employed to create a surrogate genomic signature of the imaging signature. We conducted further validation using data from five gene expression cohorts (n=639), and built a composite signature by integrating with the cell-cycle progression (CCP) score and clinical variables. Results An imaging signature consisting of pleural contact index and normalized inverse difference was significantly associated with overall survival in both imaging cohorts (p=0.0005 and 0.0009). Functional enrichment analysis revealed that genes highly correlated with the imaging signature were related to immune response, such as lymphocyte activation and chemotaxis (false discovery rate<0.05). A genomic surrogate of the imaging signature remained a significant predictor of survival adjusting for known prognostic factors (hazard ratio: 1.81, 95% CI: 1.34-2.44, p<0.0001), and stratified patients within subgroups as defined by stage, histology, or CCP score. A composite signature outperformed the genomic surrogate, CCP score, and clinical model alone (p<0.01) regarding concordance index (0.70 vs 0.62-0.63). Conclusion The proposed CT imaging signature reflects fundamental biologic differences in tumors and predicts overall survival in patients with stage I NSCLC. When combined with established prognosticators, the imaging signature improves survival prediction.


We identified a CT imaging signature that predicts overall survival in stage I NSCLC. The imaging signature is associated with immune response and may serve as a noninvasive prognostic biomarker in stage I NSCLC.

Publisher URL: www.sciencedirect.com/science

DOI: S0360301618300063

You might also like
Never Miss Important Research

Researcher is an app designed by academics, for academics. Create a personalised feed in two minutes.
Choose from over 15,000 academics journals covering ten research areas then let Researcher deliver you papers tailored to your interests each day.

  • Download from Google Play
  • Download from App Store
  • Download from AppInChina

Researcher displays publicly available abstracts and doesn’t host any full article content. If the content is open access, we will direct clicks from the abstracts to the publisher website and display the PDF copy on our platform. Clicks to view the full text will be directed to the publisher website, where only users with subscriptions or access through their institution are able to view the full article.