ESTRO 2024 - Abstract Book

S3936

Physics - Image acquisition and processing

ESTRO 2024

A convolutional neural network (CNN) model, EfficientNet-B1, was modified and trained with a learning rate of 9x10 6 , to perform multi-label image classification of SE, CC, and AC errors. The model's performance was assessed by calculating the metrics: Accuracy, Precision, Recall, and F1-score.

A retrospective analysis of the clinical data of the PR measurements received by the seven patients was performed relative to the images generated by the OpenReggui direct ray-tracing method. The simulation algorithm was