Can a Convolutional Neural Network Classify Knee Osteoarthritis on Plain Radiographs as Accurately as Fellowship-Trained Knee Arthroplasty Surgeons?
artificial intelligence
convolutional neural network
deep learning
deep neural networking
knee osteoarthritis
total knee arthroplasty
Journal
The Journal of arthroplasty
ISSN: 1532-8406
Titre abrégé: J Arthroplasty
Pays: United States
ID NLM: 8703515
Informations de publication
Date de publication:
09 2020
09 2020
Historique:
received:
19
12
2019
revised:
13
04
2020
accepted:
19
04
2020
pubmed:
19
5
2020
medline:
24
3
2021
entrez:
19
5
2020
Statut:
ppublish
Résumé
Osteoarthritis (OA) is the leading cause of disability among adults in the United States. As the diagnosis is based on the accurate interpretation of knee radiographs, use of a convolutional neural network (CNN) to grade OA severity has the potential to significantly reduce variability. Knee radiographs from consecutive patients presenting to a large academic arthroplasty practice were obtained retrospectively. These images were rated by 4 fellowship-trained knee arthroplasty surgeons using the International Knee Documentation Committee (IKDC) scoring system. The intraclass correlation coefficient (ICC) for surgeons alone and surgeons with a CNN that was trained using 4755 separate images were compared. Two hundred eighty-eight posteroanterior flexion knee radiographs (576 knees) were reviewed; 131 knees were removed due to poor quality or prior TKA. Each remaining knee was rated by 4 blinded surgeons for a total of 1780 human knee ratings. The ICC among the 4 surgeons for all possible IKDC grades was 0.703 (95% confidence interval [CI] 0.667-0.737). The ICC for the 4 surgeons and the trained CNN was 0.685 (95% CI 0.65-0.719). For IKDC D vs any other rating, the ICC of the 4 surgeons was 0.713 (95% CI 0.678-0.746), and the ICC of 4 surgeons and CNN was 0.697 (95% CI 0.663-0.73). A CNN can identify and classify knee OA as accurately as a fellowship-trained arthroplasty surgeon. This technology has the potential to reduce variability in the diagnosis and treatment of knee OA.
Sections du résumé
BACKGROUND
Osteoarthritis (OA) is the leading cause of disability among adults in the United States. As the diagnosis is based on the accurate interpretation of knee radiographs, use of a convolutional neural network (CNN) to grade OA severity has the potential to significantly reduce variability.
METHODS
Knee radiographs from consecutive patients presenting to a large academic arthroplasty practice were obtained retrospectively. These images were rated by 4 fellowship-trained knee arthroplasty surgeons using the International Knee Documentation Committee (IKDC) scoring system. The intraclass correlation coefficient (ICC) for surgeons alone and surgeons with a CNN that was trained using 4755 separate images were compared.
RESULTS
Two hundred eighty-eight posteroanterior flexion knee radiographs (576 knees) were reviewed; 131 knees were removed due to poor quality or prior TKA. Each remaining knee was rated by 4 blinded surgeons for a total of 1780 human knee ratings. The ICC among the 4 surgeons for all possible IKDC grades was 0.703 (95% confidence interval [CI] 0.667-0.737). The ICC for the 4 surgeons and the trained CNN was 0.685 (95% CI 0.65-0.719). For IKDC D vs any other rating, the ICC of the 4 surgeons was 0.713 (95% CI 0.678-0.746), and the ICC of 4 surgeons and CNN was 0.697 (95% CI 0.663-0.73).
CONCLUSIONS
A CNN can identify and classify knee OA as accurately as a fellowship-trained arthroplasty surgeon. This technology has the potential to reduce variability in the diagnosis and treatment of knee OA.
Identifiants
pubmed: 32418746
pii: S0883-5403(20)30447-2
doi: 10.1016/j.arth.2020.04.059
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
2423-2428Informations de copyright
Copyright © 2020 Elsevier Inc. All rights reserved.