Complementary Value of Intra- and Peri-Tumoral PET/CT Radiomics for Outcome Prediction in Head and Neck Cancer

Abstract

To investigate the prognostic value of peri-tumoral radiomics features of pre-treatment PET/CT images in patients with head and neck cancer. 166 patients from 4 centers (111 for training and 55 for external independent testing) were retrospectively analyzed. 11 regions were used for feature extraction, (1) Intra-tumoral region (Intra) was first dilated radially along the edge by 3, 6, 9, 12 and 15 mm to obtain (2) 5 solid combined regions (noted as Comb_3, 6, 9, 12, and 15, respectively), and (3) 5 hollow annular regions with equal ring width of 3 mm were then generated as peri-tumoral regions (noted as Peri_3, 6, 9, 12 and 15, respectively). 92 individual/integrated models were constructed by using features from Clinical alone, CT or PET alone, Clinical+PET, Clinical+CT, PET+CT, Clinical+PET+CT, Intra+Peri, Clinical+Intra+Peri and Clinical+PET+CT (Intra+Peri). In individual models, only 4 models showed p<0.05 (PET_Peri_3 and PET_Comb_6 for distant metastasis (DM) prediction, Clinical and PET_Peri_6 for death prediction). In integrated models, Clinical+CT (Intra+Peri_6), PET (Intra+Peri_3) and Clinical+PET_Peri_6 achieved the best performance for the prediction of local recurrence (LR), DM and death with AUC of 0.75, 0.80 and 0.87, C-index of 0.71, 0.80 and 0.83, p-value of 0.003, 0.008 and 0.001, respectively. Peri-tumoral regions that located closer to the intra-tumoral region (Peri_3 and Peri_6) showed better performance compared to those located further. The integration of intra-tumoral and peritumoral radiomics features achieved better performance than either of them alone, PET and CT radiomics features also provided complementary information to clinical features.

From Head and Neck Tumour and Lymph Node Segmentation to Survival Prediction on PET/CT: An End-to-End Framework Featuring Uncertainty, Fairness, and Multi-Region Multi-Modal Radiomics

“…Several studies have shown that radiomics in CT has the potential to improve the prediction of the prognosis of H&N cancer [ 23 , 24 , 25 ]. Some studies have also investigated the use of radiomics in both CT and PET for survival analysis for H&N cancer [ 26 , 27 ]. While these studies investigate the prognostic potential of CT and PET radiomics based on primary tumour delineation, there is a need to quantify the prognostic potential of radiomics features extracted from different regions of interest (ROI) such as the primary tumour and lymph nodes.…”

Identification of Stage IIIC/IV EGFR-Mutated Non-Small Cell Lung Cancer Populations Sensitive to Targeted Therapy Based on a PET/CT Radiomics Risk Model

“…Herein, we used supervoxel-based contour randomization (24) to create perturbed ROIs in PET and CT images of 60 randomly selected patients, respectively. Having 60 patients (120 PET and CT ROIs) perturbed would have made it possible to assess the robustness of feature extraction (34)(35)(36). Furthermore, due to the perturbed ROIs may deviate from tumor region, even include some non-tumor slices (Supplementary Figure S1), which may leads to unnecessary removal of features in robustness assessment, the perturbed results were further checked and adjusted slice by slice, which is also a time-consuming process.…”

Context-Aware Saliency Guided Radiomics: Application to Prediction of Outcome and HPV-Status from Multi-Center PET/CT Images of Head and Neck Cancer

“…Five HNC data collections consisting of a total of 806 patients from 9 centers were obtained: (1) The Head-Neck-PET-CT collection provided by Vallières et al, including 296 patients from 4 centers in Canada, i.e., Centre hospitalier de l’Université de Montréal (CHUM, n = 65), Centre hospitalier universitaire de Sherbrooke (CHUS, n = 100), Hôpital général juif (HGJ, n = 90) de Montréal, and Hôpital Maisonneuve-Rosemont (HMR, n = 41) de Montréal. Our previous studies [ 27 , 28 ] on multi-level multi-modality fusion radiomics and peri-tumor radiomics were conducted based on this collection. (2) The HNSCC collection provided by Grossberg et al included 159 patients from the MD Anderson Cancer Center, denoted as MDACC.…”