Publications by authors named "Nathan Benzazon"
. Severe radiation-induced lymphopenia occurs in 40% of patients treated for primary brain tumors and is an independent risk factor of poor survival outcomes. We developed anframework that estimates the radiation doses received by lymphocytes during volumetric modulated arc therapy brain irradiation.
View Article and Find Full Text PDFArticle Synopsis
- The study investigates the out-of-field dose delivered during external photon beam radiation therapy, as it may lead to a higher risk of second cancers and affect immune system efficiency in radio-immunotherapy treatments.
- Traditional methods for estimating out-of-field doses are complex and not suitable for clinical use, prompting the exploration of deep learning techniques for more effective dose map prediction.
- A 3D U-Net model, trained on data from 3,151 pediatric patients, demonstrated promising results in estimating out-of-field doses, achieving low error rates in both training and validation, indicating potential for clinical application.
A growing body of scientific evidence indicates that exposure to low dose ionizing radiation (< 2 Gy) is associated with a higher risk of developing radio-induced cancer. Additionally, it has been shown to have significant impacts on both innate and adaptive immune responses. As a result, the evaluation of the low doses inevitably delivered outside the treatment fields (out-of-field dose) in photon radiotherapy is a topic that is regaining interest at a pivotal moment in radiotherapy.
View Article and Find Full Text PDFArticle Synopsis
- The study evaluates how various factors affect the quality of pseudo computed tomography (pCT) generated from magnetic resonance imaging (MRI) using a 3D convolutional neural network (CNN).
- It includes analysis of 402 brain tumor cases, examining different MRI sequences and standardization approaches, while also comparing two specific neural network architectures (HighResNet and 3D UNet).
- Results show that larger training datasets improve pCT quality, with the best pCTs produced from >200 samples, and reveal that specific standardization methods (like white stripe) yield lower errors compared to others.