Quantitative computed tomographic descriptors associate tumor shape complexity and intratumor heterogeneity with prognosis in lung adenocarcinoma

Abstract

Two CT features were developed to quantitatively describe lung adenocarcinomas by scoring tumor shape complexity (feature 1: convexity) and intratumor density variation (feature 2: entropy ratio) in routinely obtained diagnostic CT scans. The developed quantitative features were analyzed in two independent cohorts (cohort 1: n = 61; cohort 2: n = 47) of patients diagnosed with primary lung adenocarcinoma, retrospectively curated to include imaging and clinical data. Preoperative chest CTs were segmented semi-automatically. Segmented tumor regions were further subdivided into core and boundary sub-regions, to quantify intensity variations across the tumor. Reproducibility of the features was evaluated in an independent test-retest dataset of 32 patients. The proposed metrics showed high degree of reproducibility in a repeated experiment (concordance, CCC≥0.897; dynamic range, DR≥0.92). Association with overall survival was evaluated by Cox proportional hazard regression, Kaplan-Meier survival curves, and the log-rank test. Both features were associated with overall survival (convexity: p = 0.008; entropy ratio: p = 0.04) in Cohort 1 but not in Cohort 2 (convexity: p = 0.7; entropy ratio: p = 0.8). In both cohorts, these features were found to be descriptive and demonstrated the link between imaging characteristics and patient survival in lung adenocarcinoma.

Fig 1. Convexity feature was developed to quantify tumor shape.

Convexity is computed as a ratio of tumor border (blue) to convex hull (red) (a). Convexity feature tracks the change in tumor morphology (b). Convexity is predictive of patient overall survival when dichotomized at the median value (c).

Fig 2. Entropy ratio was developed to quantify intensity variations across the tumor.

While some tumors present with consistent mean entropy across the core and the boundary (a), others have a distinct difference in the values (b).

Fig 3. Entropy ratio between the core and border regions of the tumor is predictive of patient survival.

The tumors in the two prognostic groups (a) did not appear significantly different in the CT scans (b).

Fig 4. Histogram of the two imaging features across cohorts.

Convexity (a) shows similar range across cohorts (training-green, test-blue) However, training cohort is enriched with round tumors. The range of values for entropy ratio feature (b) is larger in training cohort. Both convexity (a) and entropy ratio (b) consistently capture targeted tumor characteristics in both cohorts.