About this document
Deep Learning for In-Vivo Dosimetry by maramskshbair is a document available to read on EtoBox.
This document discusses a deep learning methodology for in-vivo dose reconstruction using Electronic Portal Imaging Devices (EPIDs) in radiotherapy. The proposed U-net architecture converts EPID responses into 2D dose distributions, aiming to improve treatment verification while bypassing complex calibration steps. The initial results indicate high accuracy in specific cases, but further improvements are needed for consistent performance across diverse test samples.
- Author
- maramskshbair
- Language
- EN