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

Abstract

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 CT , CTV CT ), PET (GTV PET40 , CTV PET40 ), and RFMs (GTV RFM , CTV RFM ,). Intratumoral heterogeneity areas were segmented as GTV PET50-Boost and radiomic boost target volume (RTV Boost ) on PET and RFMs, respectively. GTV CT in homogenous tumors and GTV PET40 in heterogeneous tumors were considered as GTV gold standard (GTV GS ). One-way analysis of variance was conducted to determine the threshold that finds the best conformity for GTV RFM with GTV GS . 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 RFM-entropy , GTV RFM-contrast , and GTV RFM-H-correlation with GTV GS , respectively. The linear regression results showed a positive correlation between GTV GS and GTV RFM-entropy (r = 0.98, p < 0.001), between GTV GS and GTV RFM-contrast (r = 0.93, p < 0.001), and between GTV GS and GTV RFM-H-correlation (r = 0.91, p < 0.001). The average threshold values of 45% and 15% were resulted in the best segmentation matching between CTV RFM-entropy and CTV RFM-contrast with CTV GS , respectively. Moreover, we used RFM to determine RTV Boost in the heterogeneous tumors. Comparison of RTV Boost with GTV PET50-Boost MAPE showed the volume error differences of 31.7%, 36%, and 34.7% in RTV Boost-entropy , RTV Boost-contrast , and RTV Boost-H-correlation , 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.

Radiotherapy modification based on artificial intelligence and radiomics applied to (18F)-fluorodeoxyglucose positron emission tomography/computed tomography

“…Another study of 32 patients treated with RT for non-small cell lung cancer evaluated the potential benefits of ( 18 F)-FDG PET/CT radiomic feature maps (RFMs) for delineating target volumes for radiation therapy [29]. The authors showed the relevance of second-order PET features for accurate identification of tumor volume with very good correlation with 40% of SUV max volume and delineation of intratumor heterogeneity with identification of tumor subvolumes.…”