A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging.
Convolutional Neural Network (CNN)
Education
Research Design
Statistics
Supervised Learning
Technical Aspects
Journal
Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556
Informations de publication
Date de publication:
Jul 2023
Jul 2023
Historique:
received:
27
10
2022
revised:
02
05
2023
accepted:
10
05
2023
medline:
2
8
2023
pubmed:
2
8
2023
entrez:
2
8
2023
Statut:
epublish
Résumé
Artificial intelligence (AI) is being increasingly used to automate and improve technologies within the field of medical imaging. A critical step in the development of an AI algorithm is estimating its prediction error through cross-validation (CV). The use of CV can help prevent overoptimism in AI algorithms and can mitigate certain biases associated with hyperparameter tuning and algorithm selection. This article introduces the principles of CV and provides a practical guide on the use of CV for AI algorithm development in medical imaging. Different CV techniques are described, as well as their advantages and disadvantages under different scenarios. Common pitfalls in prediction error estimation and guidance on how to avoid them are also discussed.
Identifiants
pubmed: 37529208
doi: 10.1148/ryai.220232
pmc: PMC10388213
doi:
Types de publication
Journal Article
Review
Langues
eng
Pagination
e220232Informations de copyright
© 2023 by the Radiological Society of North America, Inc.
Déclaration de conflit d'intérêts
Disclosures of conflicts of interest: T.J.B. No relevant relationships. Z.H. No relevant relationships. J.H. No relevant relationships. A.R. Chair of the Artificial Intelligence Task Force of the Society of Nuclear Medicine & Molecular Imaging.
Références
Neuroimage. 2017 Jan 15;145(Pt B):166-179
pubmed: 27989847
J Nucl Med. 2022 Apr;63(4):500-510
pubmed: 34740952
Gigascience. 2017 May 1;6(5):1-9
pubmed: 28327985
Med Image Anal. 2021 Dec;74:102216
pubmed: 34492574
Proc ACM Conf Health Inference Learn (2020). 2020 Apr;2020:151-159
pubmed: 33196064
J Am Coll Radiol. 2021 Aug;18(8):1143-1152
pubmed: 33819478
PET Clin. 2022 Jan;17(1):13-29
pubmed: 34809862
PET Clin. 2022 Jan;17(1):145-174
pubmed: 34809864
Proc Natl Acad Sci U S A. 2020 Jun 9;117(23):12592-12594
pubmed: 32457147
Stat Med. 2007 Dec 30;26(30):5499-511
pubmed: 17907249
Psychometrika. 1947 Jun;12(2):153-7
pubmed: 20254758
J Clin Epidemiol. 2003 May;56(5):441-7
pubmed: 12812818
Eur J Nucl Med Mol Imaging. 2020 Nov;47(12):2826-2835
pubmed: 32253486
Nat Commun. 2020 Oct 9;11(1):5088
pubmed: 33037212
Clin Nucl Med. 2021 Oct 1;46(10):814-819
pubmed: 34115709
N Engl J Med. 2021 Jul 15;385(3):283-286
pubmed: 34260843
Radiol Artif Intell. 2020 Sep 02;2(5):e200016
pubmed: 33937842
J Nucl Med. 2022 Sep;63(9):1288-1299
pubmed: 35618476
Biostatistics. 2020 Apr 1;21(2):345-352
pubmed: 31742354
J Am Stat Assoc. 2020;115(532):1917-1932
pubmed: 33716360
PET Clin. 2021 Oct;16(4):577-596
pubmed: 34537131
PLoS Med. 2018 Nov 6;15(11):e1002683
pubmed: 30399157
BMC Bioinformatics. 2006 Feb 23;7:91
pubmed: 16504092
IEEE Trans Pattern Anal Mach Intell. 2010 Mar;32(3):569-75
pubmed: 20075479
J Anal Test. 2018;2(3):249-262
pubmed: 30842888
J Cheminform. 2014 Mar 29;6(1):10
pubmed: 24678909
Biometrics. 2010 Dec;66(4):1185-91
pubmed: 20345498