Search

Introduction: Osimertinib is an effective treatment for metastatic NSCLC. Occasionally, thoracic radiation therapy (TRT) is delivered to patients receiving osimertinib to treat residual or progressing pulmonary tumors. Anecdotal reports suggest that the delivery of TRT in combination with osimertinib may be associated with a high risk of severe pneumonitis. Methods: A retrospective study was performed at a single academic medical center in the United States to investigate the incidence of severe pneumonitis among patients treated with combined TRT and osimertinib between June 2016 and December 2021. Baseline patient characteristics, tumor size and location, and dosimetric parameters were evaluated. The highest grade of radiation pneumonitis that developed within 6 months of treatment was scored in accordance with the Common Terminology Criteria for Adverse Events version 5.0. Results: A total of 16 patients were identified who were treated with combined TRT and osimertinib. All had a diagnosis of metastatic NSCLC. Treatment-related grade greater than or equal to 2 pneumonitis developed in 56%, grade greater than or equal to 3 in 37.5%, and grade 4 in 6.3%; no patient developed grade 5 pneumonitis. Median time to any-grade pneumonitis was 29 days (1–84 d); all patients had symptom resolution with expectant management or oral steroid therapies. All patients discovered to have grade greater than or equal to 3 pneumonitis (n = 6) received TRT to tumors located within 2 cm of the proximal bronchial tree, including tumors abutting the proximal bronchial tree (n = 2) and within the mediastinum (n = 1). Conclusions: The combination of TRT with osimertinib was associated with a high rate of severe pneumonitis that required oral steroid medications. Larger studies are needed to validate these findings and to understand the clinical and treatment factors that influence this risk and how they can be mitigated.

Purpose: Most radiomic studies use the features extracted from the manually drawn tumor contours for classification or survival prediction. However, large interobserver segmentation variations lead to inconsistent features and hence introduce more challenges in constructing robust prediction models. Here, we proposed an automatic workflow for glioblastoma (GBM) survival prediction based on multimodal magnetic resonance (MR) images. Methods and Materials: Two hundred eighty-five patients with glioma (210 GBM, 75 low-grade glioma) were included. One hundred sixty-three of the patients with GBM had overall survival data. Every patient had 4 preoperative MR images and manually drawn tumor contours. A 3-dimensional convolutional neural network, VGG-Seg, was trained and validated using 122 patients with glioma for automatic GBM segmentation. The trained VGG-Seg was applied to the remaining 163 patients with GBM to generate their autosegmented tumor contours. The handcrafted and deep learning (DL)–based radiomic features were extracted from the autosegmented contours using explicitly designed algorithms and a pretrained convolutional neural network, respectively. One hundred sixty-three patients with GBM were randomly split into training (n = 122) and testing (n = 41) sets for survival analysis. Cox regression models were trained to construct the handcrafted and DL-based signatures. The prognostic powers of the 2 signatures were evaluated and compared. Results: The VGG-Seg achieved a mean Dice coefficient of 0.86 across 163 patients with GBM for GBM segmentation. The handcrafted signature achieved a C-index of 0.64 (95% confidence interval, 0.55-0.73), whereas the DL-based signature achieved a C-index of 0.67 (95% confidence interval, 0.57-0.77). Unlike the handcrafted signature, the DL-based signature successfully stratified testing patients into 2 prognostically distinct groups. Conclusions: The VGG-Seg generated accurate GBM contours from 4 MR images. The DL-based signature achieved a numerically higher C-index than the handcrafted signature and significant patient stratification. The proposed automatic workflow demonstrated the potential of improving patient stratification and survival prediction in patients with GBM.