RESUMO
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.
Assuntos
Neoplasias Laríngeas , Estudos de Coortes , Humanos , Quimioterapia de Indução , Neoplasias Laríngeas/diagnóstico por imagem , Neoplasias Laríngeas/tratamento farmacológico , Curva ROC , Tomografia Computadorizada por Raios XRESUMO
BACKGROUND: In the Yttrium-90 Microspheres in Cholangiocarcinoma (MISPHEC) single-arm phase 2 trial, concomitant chemotherapy and selective internal radiotherapy (SIRT) showed antitumor activity as a first-line treatment of unresectable intrahepatic cholangiocarcinomas (ICCs). In this sub-analysis, we aimed to evaluate one of the secondary endpoints, the health-related quality of life (QoL), evaluated with an EORTC QLQ-C30 instrument at the baseline and during treatment. METHODS: The MISPHEC trial included treatment-naïve patients with an unresectable ICC between November 2013 and June 2016. Patients received concomitant first-line chemotherapy with cisplatin and gemcitabine for 8 cycles; SIRT was administered during cycle 1 (for patients with unilobar disease) or cycles 1 and 3 (for patients with bilobar disease) using glass Yttrium-90 microspheres. We evaluated the QoL-measured by the QLQ-C30 questionnaire-at the baseline, every 8 weeks during chemotherapy and follow-up, between 12 and 15 weeks after embolization and every 12 weeks after a liver resection if applicable. RESULTS: A total of 41 patients were included, of which 34 completed questionnaires at the baseline. No clinically significant changes in the global health score or the sub-scales of the QLQ-C30 were observed during follow-up. The physical, social and role function mean score worsened during treatment and fatigue, nausea and pain scores increased although the differences were not clinically significant. In patients undergoing subsequent surgery, the QoL was not impaired. CONCLUSIONS: A combination of SIRT and chemotherapy with gemcitabine and cisplatin as the first-line treatment of unresectable ICCs was found to maintain the QoL.