-
Tytuł:
-
Artificial intelligence for quality assurance in radiotherapy.
-
Autorzy:
-
Simon L; Institut Claudius-Regaud, Institut Universitaire du Cancer de Toulouse-Oncopole (IUCT-O), Toulouse, France; Centre de recherches en Cancérologie de Toulouse (CRCT), Université de Toulouse, UPS, Inserm U1037, Toulouse, France. Electronic address: .
Robert C; Université Paris-Saclay, Gustave-Roussy, Inserm, Radiothérapie Moléculaire et Innovation Thérapeutique, Villejuif, France; Department of Radiotherapy, Gustave-Roussy, Villejuif, France.
Meyer P; Service d'oncologie radiothérapie, Institut de Cancérologie Strasbourg Europe, Strasbourg, France.
-
Źródło:
-
Cancer radiotherapie : journal de la Societe francaise de radiotherapie oncologique [Cancer Radiother] 2021 Oct; Vol. 25 (6-7), pp. 623-626. Date of Electronic Publication: 2021 Jun 24.
-
Typ publikacji:
-
Journal Article; Review
-
Język:
-
English
-
Imprint Name(s):
-
Original Publication: Paris : Elsevier, c1997-
-
MeSH Terms:
-
Artificial Intelligence*
Quality Assurance, Health Care/*methods
Radiotherapy/*standards
Algorithms ; Feasibility Studies ; Humans ; Machine Learning ; Neural Networks, Computer ; Phantoms, Imaging ; Poisson Distribution ; Workload
-
Contributed Indexing:
-
Keywords: Assurance qualité; Machine learning; Quality assurance; Radiotherapy; Radiothérapie
-
Entry Date(s):
-
Date Created: 20210628 Date Completed: 20210930 Latest Revision: 20210930
-
Update Code:
-
20240105
-
DOI:
-
10.1016/j.canrad.2021.06.012
-
PMID:
-
34176724
-
In radiotherapy, patient-specific quality assurance is very time-consuming and causes machine downtime. It consists of testing (using measurement with a phantom and detector) if a modulated plan is correctly delivered by a treatment unit. Artificial intelligence and in particular machine learning algorithms were mentioned in recent reports as promising solutions to reduce or eliminate the patient-specific quality assurance workload. Several teams successfully experienced a virtual patient-specific quality assurance by training a machine learning tool to predict the results. Training data are generally composed of previous treatment plans and associated patient-specific quality assurance results. However, other training data types were recently introduced such as actual positions and velocities of multileaf collimators, metrics of the plan's complexity, and gravity vectors. Different types of machine learning algorithms were investigated (Poisson regression algorithms, convolutional neural networks, support vector classifiers) with sometimes promising results. These tools are being used for treatment units' quality assurance as well, in particular to analyse the results of imaging devices. Most of these reports were feasibility studies. Using machine learning in clinical routines as a tool that could fully replace quality assurance tests conducted by physics teams has yet to be implemented.
(Copyright © 2021 Société française de radiothérapie oncologique (SFRO). Published by Elsevier Masson SAS. All rights reserved.)