Lung adenocarcinoma (LUAD), the most common type of lung cancer, has an average 5-year survival rate of15%. In LUAD, interaction between tumor and immune cells has been shown to be highly associated with thelikelihood of disease progression and metastases. We have previously demonstrated the association between spatialarchitecture and arrangement of tumor-infiltrating lymphocytes (TILs) with likelihood of recurrence in earlystage NSCLC. Recently, gene set enrichment analysis-derived immune scores have been found to be prognostic ofoutcome. However, this requires transcriptomics techniques as a precursor, which involves mechanical disruptionof cells and tissues. In this work (N = 170), we extracted graph-based histomorphometric features on segmentednuclei from digitized H&E biopsy images and then performed principal component analysis (PCA) to selectthe most representative tiles from each patient. We then identified TILs and quantitative histomorphometricattributes of different nuclei groups (all-nuclei, TILs, non-TILs) prognostic of overall patient survival (OS) andfurther investigated their associations with immune scores and biological pathways implicated immune responseusing gene-set enrichment analysis (GSEA).We found TIL-compactness (a set of TIL density features) derived risk scores were prognostic of OS (HazardRatio (HR) = 3.26, p = 0.012, C-index = 0.634). The median immune score (IS) in the cohort was usedas a threshold to divide the cases into low and high IS expression groups. The TIL compactness measuresprognostic of OS were also statistically significantly correlated with the IS and biological pathways relatedto immune response (Immune System Process, Immune Response, Adaptive Immune Response, and HumoralImmune Response Mediated by Circulating Immunoglobulin).
展开▼
