A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

Coen Hurkmans; Jean Emmanuel Bibault; Kristy K. Brock; Wouter van Elmpt; Mary Feng; Clifton David Fuller; Barbara A. Jereczek-Fossa; Stine Korreman; Guillaume Landry; Frederic Madesta; Chuck Mayo; Alan McWilliam; Filipe Moura; Ludvig P. Muren; Issam El Naqa; Jan Seuntjens; Vincenzo Valentini; Michael Velec

doi:10.1016/j.radonc.2024.110345

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

Coen Hurkmans^*, Jean Emmanuel Bibault, Kristy K. Brock, Wouter van Elmpt, Mary Feng, Clifton David Fuller, Barbara A. Jereczek-Fossa, Stine Korreman, Guillaume Landry, Frederic Madesta, Chuck Mayo, Alan McWilliam, Filipe Moura, Ludvig P. Muren, Issam El Naqa, Jan Seuntjens, Vincenzo Valentini, Michael Velec

^*Corresponding author for this work

Department of Clinical Medicine - DCPT - Danish Center for Particle Therapy

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

15 Citations (Scopus)

Abstract

Background and purpose: Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap. Methods and materials: A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended. Results: The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated. Conclusion: A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

Original language	English
Article number	110345
Journal	Radiotherapy and Oncology
Volume	197
ISSN	0167-8140
DOIs	https://doi.org/10.1016/j.radonc.2024.110345
Publication status	Published - Aug 2024

Keywords

Artificial Intelligence
Deep learning
Ethics
Guideline
Machine Learning
Quality Assurance
Radiation Therapy
Segmentation
Treatment planning

Access to Document

10.1016/j.radonc.2024.110345Licence: CC BY

Cite this

Hurkmans, C., Bibault, J. E., Brock, K. K., van Elmpt, W., Feng, M., David Fuller, C., Jereczek-Fossa, B. A., Korreman, S., Landry, G., Madesta, F., Mayo, C., McWilliam, A., Moura, F., Muren, L. P., El Naqa, I., Seuntjens, J., Valentini, V., & Velec, M. (2024). A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy. Radiotherapy and Oncology, 197, Article 110345. https://doi.org/10.1016/j.radonc.2024.110345

@article{a2dc8acd2f4f48d1ab88853da6c2ca65,

title = "A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy",

abstract = "Background and purpose: Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap. Methods and materials: A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended. Results: The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated. Conclusion: A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.",

keywords = "Artificial Intelligence, Deep learning, Ethics, Guideline, Machine Learning, Quality Assurance, Radiation Therapy, Segmentation, Treatment planning",

author = "Coen Hurkmans and Bibault, {Jean Emmanuel} and Brock, {Kristy K.} and {van Elmpt}, Wouter and Mary Feng and {David Fuller}, Clifton and Jereczek-Fossa, {Barbara A.} and Stine Korreman and Guillaume Landry and Frederic Madesta and Chuck Mayo and Alan McWilliam and Filipe Moura and Muren, {Ludvig P.} and {El Naqa}, Issam and Jan Seuntjens and Vincenzo Valentini and Michael Velec",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors",

year = "2024",

month = aug,

doi = "10.1016/j.radonc.2024.110345",

language = "English",

volume = "197",

journal = "Radiotherapy and Oncology",

issn = "0167-8140",

publisher = "Elsevier Ireland Ltd",

}

Hurkmans, C, Bibault, JE, Brock, KK, van Elmpt, W, Feng, M, David Fuller, C, Jereczek-Fossa, BA, Korreman, S, Landry, G, Madesta, F, Mayo, C, McWilliam, A, Moura, F, Muren, LP, El Naqa, I, Seuntjens, J, Valentini, V & Velec, M 2024, 'A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy', Radiotherapy and Oncology, vol. 197, 110345. https://doi.org/10.1016/j.radonc.2024.110345

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy. / Hurkmans, Coen; Bibault, Jean Emmanuel; Brock, Kristy K. et al.
In: Radiotherapy and Oncology, Vol. 197, 110345, 08.2024.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

TY - JOUR

T1 - A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

AU - Hurkmans, Coen

AU - Bibault, Jean Emmanuel

AU - Brock, Kristy K.

AU - van Elmpt, Wouter

AU - Feng, Mary

AU - David Fuller, Clifton

AU - Jereczek-Fossa, Barbara A.

AU - Korreman, Stine

AU - Landry, Guillaume

AU - Madesta, Frederic

AU - Mayo, Chuck

AU - McWilliam, Alan

AU - Moura, Filipe

AU - Muren, Ludvig P.

AU - El Naqa, Issam

AU - Seuntjens, Jan

AU - Valentini, Vincenzo

AU - Velec, Michael

PY - 2024/8

Y1 - 2024/8

N2 - Background and purpose: Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap. Methods and materials: A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended. Results: The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated. Conclusion: A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

AB - Background and purpose: Artificial Intelligence (AI) models in radiation therapy are being developed with increasing pace. Despite this, the radiation therapy community has not widely adopted these models in clinical practice. A cohesive guideline on how to develop, report and clinically validate AI algorithms might help bridge this gap. Methods and materials: A Delphi process with all co-authors was followed to determine which topics should be addressed in this comprehensive guideline. Separate sections of the guideline, including Statements, were written by subgroups of the authors and discussed with the whole group at several meetings. Statements were formulated and scored as highly recommended or recommended. Results: The following topics were found most relevant: Decision making, image analysis, volume segmentation, treatment planning, patient specific quality assurance of treatment delivery, adaptive treatment, outcome prediction, training, validation and testing of AI model parameters, model availability for others to verify, model quality assurance/updates and upgrades, ethics. Key references were given together with an outlook on current hurdles and possibilities to overcome these. 19 Statements were formulated. Conclusion: A cohesive guideline has been written which addresses main topics regarding AI in radiation therapy. It will help to guide development, as well as transparent and consistent reporting and validation of new AI tools and facilitate adoption.

KW - Artificial Intelligence

KW - Deep learning

KW - Ethics

KW - Guideline

KW - Machine Learning

KW - Quality Assurance

KW - Radiation Therapy

KW - Segmentation

KW - Treatment planning

UR - http://www.scopus.com/inward/record.url?scp=85195415796&partnerID=8YFLogxK

U2 - 10.1016/j.radonc.2024.110345

DO - 10.1016/j.radonc.2024.110345

M3 - Journal article

C2 - 38838989

AN - SCOPUS:85195415796

SN - 0167-8140

VL - 197

JO - Radiotherapy and Oncology

JF - Radiotherapy and Oncology

M1 - 110345

ER -

A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this