Potential advantages of FDG-PET radiomic feature map for target volume delineation in lung cancer radiotherapy.

PURPOSE

To investigate the potential benefits of FDG PET radiomic feature maps (RFMs) for target delineation in non-small cell lung cancer (NSCLC) radiotherapy.

METHODS

Thirty-two NSCLC patients undergoing FDG PET/CT imaging were included. For each patient, nine grey-level co-occurrence matrix (GLCM) RFMs were generated. gross target volume (GTV) and clinical target volume (CTV) were contoured on CT (GTV , CTV ), PET (GTV , CTV ), and RFMs (GTV , CTV ,). Intratumoral heterogeneity areas were segmented as GTV and radiomic boost target volume (RTV ) on PET and RFMs, respectively. GTV in homogenous tumors and GTV in heterogeneous tumors were considered as GTV (GTV ). One-way analysis of variance was conducted to determine the threshold that finds the best conformity for GTV with GTV . Dice similarity coefficient (DSC) and mean absolute percent error (MAPE) were calculated. Linear regression analysis was employed to report the correlations between the gold standard and RFM-derived target volumes.

RESULTS

Entropy, contrast, and Haralick correlation (H-correlation) were selected for tumor segmentation. The threshold values of 80%, 50%, and 10% have the best conformity of GTV , GTV , and GTV with GTV , respectively. The linear regression results showed a positive correlation between GTV and GTV (r = 0.98, p < 0.001), between GTV and GTV (r = 0.93, p < 0.001), and between GTV and GTV (r = 0.91, p < 0.001). The average threshold values of 45% and 15% were resulted in the best segmentation matching between CTV and CTV with CTV , respectively. Moreover, we used RFM to determine RTV in the heterogeneous tumors. Comparison of RTV with GTV MAPE showed the volume error differences of 31.7%, 36%, and 34.7% in RTV , RTV , and RTV , respectively.

CONCLUSIONS

FDG PET-based radiomics features in NSCLC demonstrated a promising potential for decision support in radiotherapy, helping radiation oncologists delineate tumors and generate accurate segmentation for heterogeneous region of tumors.