Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance

Liesbeth Vandewinckele; Michael Claessens; Anna Dinkla; Charlotte Brouwer; Wouter Crijns; Dirk Verellen; Wouter van Elmpt

doi:10.1016/j.radonc.2020.09.008

Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance

Liesbeth Vandewinckele, Michael Claessens, Anna Dinkla^*, Charlotte Brouwer, Wouter Crijns, Dirk Verellen, Wouter van Elmpt

^*Corresponding author for this work

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

Abstract

Artificial Intelligence (AI) is currently being introduced into different domains, including medicine. Specifically in radiation oncology, machine learning models allow automation and optimization of the workflow. A lack of knowledge and interpretation of these AI models can hold back wide-spread and full deployment into clinical practice. To facilitate the integration of AI models in the radiotherapy workflow, generally applicable recommendations on implementation and quality assurance (QA) of AI models are presented. For commonly used applications in radiotherapy such as auto-segmentation, automated treatment planning and synthetic computed tomography (sCT) the basic concepts are discussed in depth. Emphasis is put on the commissioning, implementation and case-specific and routine QA of AI models needed for a methodical introduction in clinical practice. (C) 2020 The Authors. Published by Elsevier B.V.

Original language	English
Pages (from-to)	55-66
Number of pages	12
Journal	Radiotherapy and Oncology
Volume	153
DOIs	https://doi.org/10.1016/j.radonc.2020.09.008
Publication status	Published - Dec 2020

Keywords

Artificial intelligence
Radiotherapy
Commissioning
Quality assurance
Auto-contouring
Treatment planning
CONVOLUTIONAL NEURAL-NETWORK
MODULATED ARC THERAPY
RADIATION-THERAPY
AT-RISK
OPTIMIZATION ENGINE
ACCURATE PREDICTION
PLAN QUALITY
BIG DATA
HEAD
NECK

Access to Document

10.1016/j.radonc.2020.09.008Licence: CC BY

Cite this

@article{d00c9086e8ea4c2ebcb8c29678f82eec,

title = "Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance",

abstract = "Artificial Intelligence (AI) is currently being introduced into different domains, including medicine. Specifically in radiation oncology, machine learning models allow automation and optimization of the workflow. A lack of knowledge and interpretation of these AI models can hold back wide-spread and full deployment into clinical practice. To facilitate the integration of AI models in the radiotherapy workflow, generally applicable recommendations on implementation and quality assurance (QA) of AI models are presented. For commonly used applications in radiotherapy such as auto-segmentation, automated treatment planning and synthetic computed tomography (sCT) the basic concepts are discussed in depth. Emphasis is put on the commissioning, implementation and case-specific and routine QA of AI models needed for a methodical introduction in clinical practice. (C) 2020 The Authors. Published by Elsevier B.V.",

keywords = "Artificial intelligence, Radiotherapy, Commissioning, Quality assurance, Auto-contouring, Treatment planning, CONVOLUTIONAL NEURAL-NETWORK, MODULATED ARC THERAPY, RADIATION-THERAPY, AT-RISK, OPTIMIZATION ENGINE, ACCURATE PREDICTION, PLAN QUALITY, BIG DATA, HEAD, NECK",

author = "Liesbeth Vandewinckele and Michael Claessens and Anna Dinkla and Charlotte Brouwer and Wouter Crijns and Dirk Verellen and \{van Elmpt\}, Wouter",

note = "Funding Information: We would like to thank Elizabeth Adams, Sigrun Saur Almberg, Jeremy Booth, Andrew Green, Diana Grishchuk, Matteo Maspero, David Menichelli and Carlos Rodrigues for their thoughtful review on this paper. Furthermore, this research is funded through the AI Research Program of the Flemish Government , Belgium (Liesbeth Vandewinckele) and by a grant of the Flemish League Against Cancer , Belgium, ref: 000019356 (Micha{\"e}l Claessens). Publisher Copyright: {\textcopyright} 2020",

year = "2020",

month = dec,

doi = "10.1016/j.radonc.2020.09.008",

language = "English",

volume = "153",

pages = "55--66",

journal = "Radiotherapy and Oncology",

issn = "0167-8140",

publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Overview of artificial intelligence-based applications in radiotherapy

T2 - Recommendations for implementation and quality assurance

AU - Vandewinckele, Liesbeth

AU - Claessens, Michael

AU - Dinkla, Anna

AU - Brouwer, Charlotte

AU - Crijns, Wouter

AU - Verellen, Dirk

AU - van Elmpt, Wouter

N1 - Funding Information: We would like to thank Elizabeth Adams, Sigrun Saur Almberg, Jeremy Booth, Andrew Green, Diana Grishchuk, Matteo Maspero, David Menichelli and Carlos Rodrigues for their thoughtful review on this paper. Furthermore, this research is funded through the AI Research Program of the Flemish Government , Belgium (Liesbeth Vandewinckele) and by a grant of the Flemish League Against Cancer , Belgium, ref: 000019356 (Michaël Claessens). Publisher Copyright: © 2020

PY - 2020/12

Y1 - 2020/12

N2 - Artificial Intelligence (AI) is currently being introduced into different domains, including medicine. Specifically in radiation oncology, machine learning models allow automation and optimization of the workflow. A lack of knowledge and interpretation of these AI models can hold back wide-spread and full deployment into clinical practice. To facilitate the integration of AI models in the radiotherapy workflow, generally applicable recommendations on implementation and quality assurance (QA) of AI models are presented. For commonly used applications in radiotherapy such as auto-segmentation, automated treatment planning and synthetic computed tomography (sCT) the basic concepts are discussed in depth. Emphasis is put on the commissioning, implementation and case-specific and routine QA of AI models needed for a methodical introduction in clinical practice. (C) 2020 The Authors. Published by Elsevier B.V.

AB - Artificial Intelligence (AI) is currently being introduced into different domains, including medicine. Specifically in radiation oncology, machine learning models allow automation and optimization of the workflow. A lack of knowledge and interpretation of these AI models can hold back wide-spread and full deployment into clinical practice. To facilitate the integration of AI models in the radiotherapy workflow, generally applicable recommendations on implementation and quality assurance (QA) of AI models are presented. For commonly used applications in radiotherapy such as auto-segmentation, automated treatment planning and synthetic computed tomography (sCT) the basic concepts are discussed in depth. Emphasis is put on the commissioning, implementation and case-specific and routine QA of AI models needed for a methodical introduction in clinical practice. (C) 2020 The Authors. Published by Elsevier B.V.

KW - Artificial intelligence

KW - Radiotherapy

KW - Commissioning

KW - Quality assurance

KW - Auto-contouring

KW - Treatment planning

KW - CONVOLUTIONAL NEURAL-NETWORK

KW - MODULATED ARC THERAPY

KW - RADIATION-THERAPY

KW - AT-RISK

KW - OPTIMIZATION ENGINE

KW - ACCURATE PREDICTION

KW - PLAN QUALITY

KW - BIG DATA

KW - HEAD

KW - NECK

U2 - 10.1016/j.radonc.2020.09.008

DO - 10.1016/j.radonc.2020.09.008

M3 - Article

C2 - 32920005

SN - 0167-8140

VL - 153

SP - 55

EP - 66

JO - Radiotherapy and Oncology

JF - Radiotherapy and Oncology

ER -

Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance

Abstract

Keywords

Access to Document

Fingerprint

Cite this