Using artificial intelligence to diagnose fresh osteoporotic vertebral fractures on magnetic resonance images.
Artificial intelligence
Convolutional neural network
Deep learning
Ensemble method
Fresh fracture
Magnetic resonance image
Old fracture
Osteoporosis
Osteoporotic vertebral fracture
Vertebra detection
Journal
The spine journal : official journal of the North American Spine Society
ISSN: 1878-1632
Titre abrégé: Spine J
Pays: United States
ID NLM: 101130732
Informations de publication
Date de publication:
10 2021
10 2021
Historique:
received:
26
08
2020
revised:
21
02
2021
accepted:
08
03
2021
pubmed:
17
3
2021
medline:
28
10
2021
entrez:
16
3
2021
Statut:
ppublish
Résumé
Accurate diagnosis of osteoporotic vertebral fracture (OVF) is important for improving treatment outcomes; however, the gold standard has not been established yet. A deep-learning approach based on convolutional neural network (CNN) has attracted attention in the medical imaging field. To construct a CNN to detect fresh OVF on magnetic resonance (MR) images. Retrospective analysis of MR images PATIENT SAMPLE: This retrospective study included 814 patients with fresh OVF. For CNN training and validation, 1624 slices of T1-weighted MR image were obtained and used. We plotted the receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC) in order to evaluate the performance of the CNN. Consequently, the sensitivity, specificity, and accuracy of the diagnosis by CNN and that of the two spine surgeons were compared. We constructed an optimal model using ensemble method by combining nine types of CNNs to detect fresh OVFs. Furthermore, two spine surgeons independently evaluated 100 vertebrae, which were randomly extracted from test data. The ensemble method using VGG16, VGG19, DenseNet201, and ResNet50 was the combination with the highest AUC of ROC curves. The AUC was 0.949. The evaluation metrics of the diagnosis (CNN/surgeon 1/surgeon 2) for 100 vertebrae were as follows: sensitivity: 88.1%/88.1%/100%; specificity: 87.9%/86.2%/65.5%; accuracy: 88.0%/87.0%/80.0%. In detecting fresh OVF using MR images, the performance of the CNN was comparable to that of two spine surgeons.
Sections du résumé
BACKGROUND CONTEXT
Accurate diagnosis of osteoporotic vertebral fracture (OVF) is important for improving treatment outcomes; however, the gold standard has not been established yet. A deep-learning approach based on convolutional neural network (CNN) has attracted attention in the medical imaging field.
PURPOSE
To construct a CNN to detect fresh OVF on magnetic resonance (MR) images.
STUDY DESIGN/SETTING
Retrospective analysis of MR images PATIENT SAMPLE: This retrospective study included 814 patients with fresh OVF. For CNN training and validation, 1624 slices of T1-weighted MR image were obtained and used.
OUTCOME MEASURE
We plotted the receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC) in order to evaluate the performance of the CNN. Consequently, the sensitivity, specificity, and accuracy of the diagnosis by CNN and that of the two spine surgeons were compared.
METHODS
We constructed an optimal model using ensemble method by combining nine types of CNNs to detect fresh OVFs. Furthermore, two spine surgeons independently evaluated 100 vertebrae, which were randomly extracted from test data.
RESULTS
The ensemble method using VGG16, VGG19, DenseNet201, and ResNet50 was the combination with the highest AUC of ROC curves. The AUC was 0.949. The evaluation metrics of the diagnosis (CNN/surgeon 1/surgeon 2) for 100 vertebrae were as follows: sensitivity: 88.1%/88.1%/100%; specificity: 87.9%/86.2%/65.5%; accuracy: 88.0%/87.0%/80.0%.
CONCLUSIONS
In detecting fresh OVF using MR images, the performance of the CNN was comparable to that of two spine surgeons.
Identifiants
pubmed: 33722728
pii: S1529-9430(21)00117-0
doi: 10.1016/j.spinee.2021.03.006
pii:
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1652-1658Informations de copyright
Copyright © 2021 Elsevier Inc. All rights reserved.