Knowledge Based Versus Data Based: A Historical Perspective on a Continuum of Methodologies for Medical Image Analysis.
Artificial intelligence
Computer vision
Deep learning
Machine learning
Medical image analysis
Journal
Neuroimaging clinics of North America
ISSN: 1557-9867
Titre abrégé: Neuroimaging Clin N Am
Pays: United States
ID NLM: 9211377
Informations de publication
Date de publication:
Nov 2020
Nov 2020
Historique:
entrez:
11
10
2020
pubmed:
12
10
2020
medline:
12
8
2021
Statut:
ppublish
Résumé
The advent of big data and deep learning algorithms has promoted a major shift toward data-driven methods in medical image analysis recently. However, the medical image analysis field has a long and rich history inclusive of both knowledge-driven and data-driven methodologies. In the present article, we provide a historical review of an illustrative sample of medical image analysis methods and locate them along a knowledge-driven versus data-driven continuum. In doing so, we highlight the historical importance as well as current-day relevance of more traditional, knowledge-based artificial intelligence approaches and their complementarity with fully data-driven techniques such as deep learning.
Identifiants
pubmed: 33038992
pii: S1052-5149(20)30049-6
doi: 10.1016/j.nic.2020.06.002
pii:
doi:
Types de publication
Comparative Study
Journal Article
Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
401-415Informations de copyright
Copyright © 2020 Elsevier Inc. All rights reserved.
Déclaration de conflit d'intérêts
Disclosure The authors do not have any conflict of interest to report.