ABSTRACT
Introduction: Despite radical intent therapy for patients with stage III non-small-cell lung cancer (NSCLC), cumulative incidence of brain metastases (BM) reaches 30%. Current risk stratification methods fail to accurately identify these patients. As radiomics features have been shown to have predictive value, this study aims to develop a model combining clinical risk factors with radiomics features for BM development in patients with radically treated stage III NSCLC. Methods: Retrospective analysis of two prospective multicentre studies. Inclusion criteria: adequately staged [18F-fluorodeoxyglucose positron emission tomography-computed tomography (18-FDG-PET-CT), contrast-enhanced chest CT, contrast-enhanced brain magnetic resonance imaging/CT] and radically treated stage III NSCLC, exclusion criteria: second primary within 2 years of NSCLC diagnosis and prior prophylactic cranial irradiation. Primary endpoint was BM development any time during follow-up (FU). CT-based radiomics features (N = 530) were extracted from the primary lung tumour on 18-FDG-PET-CT images, and a list of clinical features (N = 8) was collected. Univariate feature selection based on the area under the curve (AUC) of the receiver operating characteristic was performed to identify relevant features. Generalized linear models were trained using the selected features, and multivariate predictive performance was assessed through the AUC. Results: In total, 219 patients were eligible for analysis. Median FU was 59.4 months for the training cohort and 67.3 months for the validation cohort; 21 (15%) and 17 (22%) patients developed BM in the training and validation cohort, respectively. Two relevant clinical features (age and adenocarcinoma histology) and four relevant radiomics features were identified as predictive. The clinical model yielded the highest AUC value of 0.71 (95% CI: 0.58-0.84), better than radiomics or a combination of clinical parameters and radiomics (both an AUC of 0.62, 95% CIs of 0.47-076 and 0.48-0.76, respectively). Conclusion: CT-based radiomics features of primary NSCLC in the current setup could not improve on a model based on clinical predictors (age and adenocarcinoma histology) of BM development in radically treated stage III NSCLC patients.
ABSTRACT
Purpose The purpose of the current study was to investigate whether prophylactic cranial irradiation (PCI) reduces the incidence of symptomatic brain metastases in patients with stage III non-small-cell lung cancer (NSCLC) treated with curative intention. Patients and Methods Patients with stage III NSCLC-staged with a contrast-enhanced brain computed tomography or magnetic resonance imaging-were randomly assigned to either observation or PCI after concurrent/sequential chemoradiotherapy with or without surgery. The primary end point-development of symptomatic brain metastases at 24 months-was defined as one or a combination of key symptoms that suggest brain metastases-signs of increased intracranial pressure, headache, nausea and vomiting, cognitive or affective disturbances, seizures, and focal neurologic symptoms-and magnetic resonance imaging or computed tomography demonstrating the existence of brain metastasis. Adverse effects, survival, quality of life, quality-adjusted survival, and health care costs were secondary end points. Results Between 2009 and 2015, 175 patients were randomly assigned: 87 received PCI and 88 underwent observation only. Median follow-up was 48.5 months (95% CI, 39 to 54 months). Six (7.0%) of 86 patients in the PCI group and 24 (27.2%) of 88 patients in the control group had symptomatic brain metastases ( P = .001). PCI significantly increased the time to develop symptomatic brain metastases (hazard ratio, 0.23; [95% CI, 0.09 to 0.56]; P = .0012). Median time to develop brain metastases was not reached in either arm. Overall survival was not significantly different between both arms. Grade 1 and 2 memory impairment (26 of 86 v seven of 88 patients) and cognitive disturbance (16 of 86 v three of 88 patients) were significantly increased in the PCI arm. Quality of life was only decreased 3 months post-PCI and was similar to the observation arm thereafter. Conclusion PCI significantly decreased the proportion of patients who developed symptomatic brain metastases with an increase of low-grade toxicity.