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.
