Evaluation of a clinically introduced deep learning model for radiotherapy treatment planning of breast cancer

Nienke Bakx; Maurice van der Sangen; Jacqueline Theuws; Johanna Bluemink; Coen Hurkmans

doi:10.1016/j.phro.2023.100496

Evaluation of a clinically introduced deep learning model for radiotherapy treatment planning of breast cancer

Nienke Bakx
, Maurice van der Sangen
, Jacqueline Theuws
, Johanna Bluemink
, Coen Hurkmans (Corresponding author-nrf)

Research output: Contribution to journal › Article › Academic › peer-review

9 Citations (Scopus)

32 Downloads (Pure)

Abstract

Deep learning (DL) models are increasingly studied to automate the process of radiotherapy treatment planning. This study evaluates the clinical use of such a model for whole breast radiotherapy. Treatment plans were automatically generated, after which planners were allowed to manually adapt them. Plans were evaluated based on clinical goals and DVH parameters. Thirty-seven of 50plans did fulfill all clinical goals without adjustments. Thirteen of these 37 plans were still adjusted but did not improve mean heart or lung dose. These results leave room for improvement of both the DL model as well as education on clinically relevant adjustments.

Original language	English
Article number	100496
Number of pages	4
Journal	Physics and Imaging in Radiation Oncology
Volume	28
DOIs	https://doi.org/10.1016/j.phro.2023.100496
Publication status	Published - Oct 2023

Bibliographical note

Publisher Copyright:
© 2023 The Author(s)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Breast cancer
Clinical use
Deep learning
Radiotherapy

Access to Document

10.1016/j.phro.2023.100496

pdfFinal published version, 440 KBLicence: CC BY-NC-ND

Cite this

@article{b3f19bfbd89d404c92327a613ca84a4c,

title = "Evaluation of a clinically introduced deep learning model for radiotherapy treatment planning of breast cancer",

abstract = "Deep learning (DL) models are increasingly studied to automate the process of radiotherapy treatment planning. This study evaluates the clinical use of such a model for whole breast radiotherapy. Treatment plans were automatically generated, after which planners were allowed to manually adapt them. Plans were evaluated based on clinical goals and DVH parameters. Thirty-seven of 50plans did fulfill all clinical goals without adjustments. Thirteen of these 37 plans were still adjusted but did not improve mean heart or lung dose. These results leave room for improvement of both the DL model as well as education on clinically relevant adjustments.",

keywords = "Breast cancer, Clinical use, Deep learning, Radiotherapy",

author = "Nienke Bakx and \{van der Sangen\}, Maurice and Jacqueline Theuws and Johanna Bluemink and Coen Hurkmans",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s)",

year = "2023",

month = oct,

doi = "10.1016/j.phro.2023.100496",

language = "English",

volume = "28",

journal = "Physics and Imaging in Radiation Oncology",

issn = "2405-6316",

publisher = "Elsevier",

}

TY - JOUR

T1 - Evaluation of a clinically introduced deep learning model for radiotherapy treatment planning of breast cancer

AU - Bakx, Nienke

AU - van der Sangen, Maurice

AU - Theuws, Jacqueline

AU - Bluemink, Johanna

A2 - Hurkmans, Coen

PY - 2023/10

Y1 - 2023/10

N2 - Deep learning (DL) models are increasingly studied to automate the process of radiotherapy treatment planning. This study evaluates the clinical use of such a model for whole breast radiotherapy. Treatment plans were automatically generated, after which planners were allowed to manually adapt them. Plans were evaluated based on clinical goals and DVH parameters. Thirty-seven of 50plans did fulfill all clinical goals without adjustments. Thirteen of these 37 plans were still adjusted but did not improve mean heart or lung dose. These results leave room for improvement of both the DL model as well as education on clinically relevant adjustments.

AB - Deep learning (DL) models are increasingly studied to automate the process of radiotherapy treatment planning. This study evaluates the clinical use of such a model for whole breast radiotherapy. Treatment plans were automatically generated, after which planners were allowed to manually adapt them. Plans were evaluated based on clinical goals and DVH parameters. Thirty-seven of 50plans did fulfill all clinical goals without adjustments. Thirteen of these 37 plans were still adjusted but did not improve mean heart or lung dose. These results leave room for improvement of both the DL model as well as education on clinically relevant adjustments.

KW - Breast cancer

KW - Clinical use

KW - Deep learning

KW - Radiotherapy

UR - https://www.scopus.com/pages/publications/85173494220

U2 - 10.1016/j.phro.2023.100496

DO - 10.1016/j.phro.2023.100496

M3 - Article

AN - SCOPUS:85173494220

SN - 2405-6316

VL - 28

JO - Physics and Imaging in Radiation Oncology

JF - Physics and Imaging in Radiation Oncology

M1 - 100496

ER -

Evaluation of a clinically introduced deep learning model for radiotherapy treatment planning of breast cancer

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this