PROJECT TITLE :

Association between tumor heterogeneity and overall survival in patients with non-small cell lung cancer - 2016

ABSTRACT:

In this paper, a radiomics approach was proposed to determine whether the tumor heterogeneity of non-little cell lung cancer (NSCLC), that was measured by the feel on computed tomography (CT), could build an freelance prediction of overall survival. A primary dataset contained 72 patients (mean survival, 15.9 months) with pathologic diagnosis of NSCLC and a validation dataset contained 67 NSCLC (mean survival, eighteen.one months) patients which were used for prognosis trial. The experiment results indicated that the features: "energy of run-length (ERL)" (hazard ratio [HR]: 0.55, 95% confidence interval [CI]: (zero.34, 0.89), P = zero.014) and "long-run high gray level stress of run-length (LRHGLERL)" (HR: zero.50, ninety five%CI: (0.32, 0.eighty), P = zero.005) were considerably associated with overall survival in the primary dataset, and these 2 texture options conjointly create an consistent performance on the validation cohort. Our study more supported that the quantitative measurement of tumor heterogeneity can be associated with prognosis of NSCLC.