Cargando…

A convolutional neural network model for EPID‐based non‐transit dosimetry

PURPOSE: To develop an alternative computational approach for EPID‐based non‐transit dosimetry using a convolutional neural network model. METHOD: A U‐net followed by a non‐trainable layer named True Dose Modulation recovering the spatialized information was developed. The model was trained on 186 I...

Descripción completa

Detalles Bibliográficos
Autores principales: Bosco, Lucas Dal, Franceries, Xavier, Romain, Blandine, Smekens, François, Husson, François, Le Lann, Marie‐Véronique
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10243321/
https://www.ncbi.nlm.nih.gov/pubmed/36864758
http://dx.doi.org/10.1002/acm2.13923
_version_ 1785054402387640320
author Bosco, Lucas Dal
Franceries, Xavier
Romain, Blandine
Smekens, François
Husson, François
Le Lann, Marie‐Véronique
author_facet Bosco, Lucas Dal
Franceries, Xavier
Romain, Blandine
Smekens, François
Husson, François
Le Lann, Marie‐Véronique
author_sort Bosco, Lucas Dal
collection PubMed
description PURPOSE: To develop an alternative computational approach for EPID‐based non‐transit dosimetry using a convolutional neural network model. METHOD: A U‐net followed by a non‐trainable layer named True Dose Modulation recovering the spatialized information was developed. The model was trained on 186 Intensity‐Modulated Radiation Therapy Step & Shot beams from 36 treatment plans of different tumor locations to convert grayscale portal images into planar absolute dose distributions. Input data were acquired from an amorphous‐Silicon Electronic Portal Image Device and a 6 MV X‐ray beam. Ground truths were computed from a conventional kernel‐based dose algorithm. The model was trained by a two‐step learning process and validated through a five‐fold cross‐validation procedure with sets of training and validation of 80% and 20%, respectively. A study regarding the dependance of the amount of training data was conducted. The performance of the model was evaluated from a quantitative analysis based the ϒ‐index, absolute and relative errors computed between the inferred dose distributions and ground truths for six square and 29 clinical beams from seven treatment plans. These results were also compared to those of an existing portal image‐to‐dose conversion algorithm. RESULTS: For the clinical beams, averages of ϒ‐index and ϒ‐passing rate (2%‐2mm > 10% D(max)) of 0.24 (±0.04) and 99.29 (±0.70)% were obtained. For the same metrics and criteria, averages of 0.31 (±0.16) and 98.83 (±2.40)% were obtained with the six square beams. Overall, the developed model performed better than the existing analytical method. The study also showed that sufficient model accuracy can be achieved with the amount of training samples used. CONCLUSION: A deep learning‐based model was developed to convert portal images into absolute dose distributions. The accuracy obtained shows that this method has great potential for EPID‐based non‐transit dosimetry.
format Online
Article
Text
id pubmed-10243321
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-102433212023-06-07 A convolutional neural network model for EPID‐based non‐transit dosimetry Bosco, Lucas Dal Franceries, Xavier Romain, Blandine Smekens, François Husson, François Le Lann, Marie‐Véronique J Appl Clin Med Phys Radiation Oncology Physics PURPOSE: To develop an alternative computational approach for EPID‐based non‐transit dosimetry using a convolutional neural network model. METHOD: A U‐net followed by a non‐trainable layer named True Dose Modulation recovering the spatialized information was developed. The model was trained on 186 Intensity‐Modulated Radiation Therapy Step & Shot beams from 36 treatment plans of different tumor locations to convert grayscale portal images into planar absolute dose distributions. Input data were acquired from an amorphous‐Silicon Electronic Portal Image Device and a 6 MV X‐ray beam. Ground truths were computed from a conventional kernel‐based dose algorithm. The model was trained by a two‐step learning process and validated through a five‐fold cross‐validation procedure with sets of training and validation of 80% and 20%, respectively. A study regarding the dependance of the amount of training data was conducted. The performance of the model was evaluated from a quantitative analysis based the ϒ‐index, absolute and relative errors computed between the inferred dose distributions and ground truths for six square and 29 clinical beams from seven treatment plans. These results were also compared to those of an existing portal image‐to‐dose conversion algorithm. RESULTS: For the clinical beams, averages of ϒ‐index and ϒ‐passing rate (2%‐2mm > 10% D(max)) of 0.24 (±0.04) and 99.29 (±0.70)% were obtained. For the same metrics and criteria, averages of 0.31 (±0.16) and 98.83 (±2.40)% were obtained with the six square beams. Overall, the developed model performed better than the existing analytical method. The study also showed that sufficient model accuracy can be achieved with the amount of training samples used. CONCLUSION: A deep learning‐based model was developed to convert portal images into absolute dose distributions. The accuracy obtained shows that this method has great potential for EPID‐based non‐transit dosimetry. John Wiley and Sons Inc. 2023-03-02 /pmc/articles/PMC10243321/ /pubmed/36864758 http://dx.doi.org/10.1002/acm2.13923 Text en © 2023 DOSISOFT and The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Radiation Oncology Physics
Bosco, Lucas Dal
Franceries, Xavier
Romain, Blandine
Smekens, François
Husson, François
Le Lann, Marie‐Véronique
A convolutional neural network model for EPID‐based non‐transit dosimetry
title A convolutional neural network model for EPID‐based non‐transit dosimetry
title_full A convolutional neural network model for EPID‐based non‐transit dosimetry
title_fullStr A convolutional neural network model for EPID‐based non‐transit dosimetry
title_full_unstemmed A convolutional neural network model for EPID‐based non‐transit dosimetry
title_short A convolutional neural network model for EPID‐based non‐transit dosimetry
title_sort convolutional neural network model for epid‐based non‐transit dosimetry
topic Radiation Oncology Physics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10243321/
https://www.ncbi.nlm.nih.gov/pubmed/36864758
http://dx.doi.org/10.1002/acm2.13923
work_keys_str_mv AT boscolucasdal aconvolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT franceriesxavier aconvolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT romainblandine aconvolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT smekensfrancois aconvolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT hussonfrancois aconvolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT lelannmarieveronique aconvolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT boscolucasdal convolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT franceriesxavier convolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT romainblandine convolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT smekensfrancois convolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT hussonfrancois convolutionalneuralnetworkmodelforepidbasednontransitdosimetry
AT lelannmarieveronique convolutionalneuralnetworkmodelforepidbasednontransitdosimetry