Association of radiomic features with epidermal growth factor receptor mutation status in non-small cell lung cancer and survival treated with tyrosine kinase inhibitors

Assessment and Prognostic Value of Immediate Changes in Post-Ablation Intratumor Density Heterogeneity of Pulmonary Tumors via Radiomics-Based Computed Tomography Features

Objectives

To retrospectively observe the instantaneous changes in intratumor density heterogeneity after microwave ablation (MWA) of lung tumors and to determine their prognostic value in predicting treatment response and local tumor progression (LTP).

Methods

Pre- and post-MWA computed tomography (CT) images of 50 patients (37-males; 13-females; mean-age 65.9 ± 9.7y, 39 primary and 11 metastasis) were analyzed to evaluate changes in intratumor density. Global, regional, and local scale radiomics features were extracted to assess intratumor density heterogeneity. In four to six weeks, chest enhanced CT was used as the baseline evaluation of treatment response. The correlations between the parametric variation immediately after ablation and the visual score of ablation response (Rvisu) were analyzed by nonparametric Spearman correlation analysis. The 1-year LTP discrimination power was assessed using the area under the receiver operating characteristic (ROC) curves. A Cox proportional hazards regression model was used to identify the independent prognostic features.

Results

Although no significant volume changes were observed after ablation, the radiomics parameters changed in different directions and degrees. The mean intensity value from baseline CT image was 30.3 ± 23.2, and the post-MWA CT image was -60.9 ± 89.8. The ratio of values change was then calculated by a unified formulation. The largest increase (522.3%) was observed for cluster prominence, while the mean CT value showed the largest decline (321.4%). The pulmonary tumors had a mean diameter of 3.4 ± 0.8 cm. Complete ablation was documented in 36 patients. Significant correlations were observed between Rvisu and quantitative features. The highest correlations were observed for changes in local features after MWA, with r ranging from 0.594 to 0.782. LTP developed in 22 patients. The Cox regression model revealed Δcontrast% and response score as independent predictors (Δcontrast%: odds ratio [OR]=5.61, p=0.001; Rvisu: OR=1.73, p=0019). ROC curve analysis showed that Δcontrast% was a better predictor of 1-year LTP. with higher sensitivity (83.5% vs. 71.2%) and specificity (87.1% vs. 76.8%) than those for Rvisu.

Conclusions

The changes in intratumor density heterogeneity after MWA could be characterized by analysis of radiomics features. Real-time density changes could predict treatment response and LTP in patients with pulmonary tumors earlier, especially for tumors with larger diameters.

CT-based radiomics signatures can predict the tumor response of non-small cell lung cancer patients treated with first-line chemotherapy and targeted therapy

OBJECTIVES

The goal of this study was to evaluate the effectiveness of radiomics signatures on pre-treatment computed tomography (CT) images of lungs to predict the tumor responses of non-small cell lung cancer (NSCLC) patients treated with first-line chemotherapy, targeted therapy, or a combination of both.

MATERIALS AND METHODS

This retrospective study included 322 NSCLC patients who were treated with first-line chemotherapy, targeted therapy, or a combination of both. Of these patients, 224 were randomly assigned to a cohort to help develop the radiomics signature. A total of 1946 radiomics features were obtained from each patient's CT scan. The top-ranked features were selected by the Minimum Redundancy Maximum Relevance (MRMR) feature-ranking method and used to build a lightweight radiomics signature with the Random Forest (RF) classifier. The independent predictive (IP) features (AUC > 0.6, p value < 0.05) were further identified from the top-ranked features and used to build a refined radiomics signature by the RF classifier. Its prediction performance was tested on the validation cohort, which consisted of the remaining 98 patients.

RESULTS

The initial lightweight radiomics signature constructed from 15 top-ranked features had an AUC of 0.721 (95% CI, 0.619-0.823). After six IP features were further identified and a refined radiomics signature was built, it had an AUC of 0.746 (95% CI, 0.646-0.846).

CONCLUSIONS

Radiomics signatures based on pre-treatment CT scans can accurately predict tumor response in NSCLC patients after first-line chemotherapy or targeted therapy treatments. Radiomics features could be used as promising prognostic imaging biomarkers in the future.

KEY POINTS

The radiomics signature extracted from baseline CT images in patients with NSCLC can predict response to first-line chemotherapy, targeted therapy, or both treatments with an AUC = 0.746 (95% CI, 0.646-0.846). The radiomics signature could be used as a new biomarker for quantitative analysis in radiology, which might provide value in decision-making and to define personalized treatments for cancer patients.