N3 (> 6 cm) squamous cell carcinoma of the head and neck: outcomes and predictive factors in 104 patients.

OBJECTIVE: To report outcome and predictive factors in patients with N3 (> 6 cm) non-metastatic locally advanced head and neck squamous cell carcinoma (LAHNSCC) treated with a conservative approach or with initial surgery. METHODS: 104 patients were included: 69 treated with radiotherapy (RT) ± chemotherapy (CT) and 35 with nodal surgery with or without primary tumour resection, which was completed in 30 patients by adjuvant RT ± CT. Positron-emission tomography-computed tomography (PET-CT) guided surveillance after RT ± CT was standard. RESULTS: Two-year overall survival (OS) and locoregional control (LRC) were 39.4% and 37.5%, respectively. In univariate analysis, body mass index (BMI), performance status (PS), p16 status and haemoglobin value influenced OS and disease-free survival (DFS). In multivariate analysis, p16 positive status and BMI ≥ 25 remained independent prognostic factors for better OS (p = 0.023) and DFS (p = 0.002). Only under/normal weight remained an independent and adverse significant prognostic factor in multivariate analysis for regional control (RC). Patients treated with primary RT ± CT had slightly better 2-year OS (43.5% versus 33.3%, p = 0.31). CONCLUSIONS: Patients with N3 LAHNSCC have poor prognosis, but long term LRC is achievable, especially in overweight patients and those with a good PS.

Statistical harmonization can improve the development of a multicenter CT-based radiomic model predictive of nonresponse to induction chemotherapy in laryngeal cancers.

PURPOSE: To develop a radiomic model predicting nonresponse to induction chemotherapy in laryngeal cancers, from multicenter pretherapeutic contrast-enhanced computed tomography (CE-CT) and evaluate the benefit of feature harmonization in such a context. METHODS: Patients (n = 104) eligible for laryngeal preservation chemotherapy were included in five centers. Primary tumor was manually delineated on the CE-CT images. The following radiomic features were extracted with an in-house software (MIRAS v1.1, LaTIM UMR 1101): intensity, shape, and textural features derived from Gray-Level Co-occurrence Matrix (GLCM), Neighborhood Gray Tone Difference Matrix (NGTDM), Gray-Level Run Length Matrix (GLRLM), and Gray-Level Size Zone Matrix (GLSZM). Harmonization was performed using ComBat after unsupervised hierarchical clustering, used to determine labels automatically, given the high heterogeneity of imaging characteristics across and within centers. Patients with similar feature distributions were grouped with unsupervised clustering into an optimal number of clusters (2) determined with "silhouette scoring." Statistical harmonization was then carried out with ComBat on these 2 identified clusters. The cohort was split into training/validation (n = 66) and testing (n = 32) sets. Area under the receiver operating characteristics curves (AUC) were used to evaluate the ability of radiomic features (before and after harmonization) to predict nonresponse to chemotherapy, and specificity (Sp) and sensitivity (Se) were used to quantify their performance in the testing set. RESULTS: Without harmonization, none of the features identified as predictive in the training set remained significant in the testing set. After ComBat, one textural feature identified in the training set keeps a predictive trend in the testing set-Zone Percentage, derived from the GLSZM, was predictive of nonresponse in the training set (AUC = 0.62, Se = 70%, Sp = 64%, P = 0.04) and obtained a satisfactory performance in the testing set (Se = 80%, Sp = 67%, P = 0.03), although significance was limited by the size of the testing set. These results are consistent with previously published findings in head and neck cancers. CONCLUSIONS: Radiomic features from CE-CT could help in the selection of patients for induction chemotherapy in laryngeal cancers, with relatively good sensitivity and specificity in predicting lack of response. Statistical harmonization with ComBat and unsupervised clustering seems to improve the predictive value of features extracted in such a heterogeneous multicenter setting.