Development and validation of a deep learning model using convolutional neural networks to identify femoral internal fixation device in radiographs.
Artificial intelligence
Convolutional neural network
Deep learning
Internal fixation device
Proximal femur fracture
Journal
Skeletal radiology
ISSN: 1432-2161
Titre abrégé: Skeletal Radiol
Pays: Germany
ID NLM: 7701953
Informations de publication
Date de publication:
Aug 2023
Aug 2023
Historique:
received:
02
02
2023
accepted:
13
03
2023
revised:
13
03
2023
medline:
19
6
2023
pubmed:
26
3
2023
entrez:
25
3
2023
Statut:
ppublish
Résumé
The purpose of this study is to develop and validate a deep convolutional neural network (DCNN) model to automatically identify the manufacturer and model of hip internal fixation devices from anteroposterior (AP) radiographs. In this retrospective study, 1721 hip AP radiographs, including six internal fixation devices from 1012 patients, were collected from an orthopedic center between June 2014 and June 2022 to establish a classification network. The images were divided into training set (1106 images), validation set (272 images), and test set (343 images). The model efficacy is evaluated by using the data on the test set. The overall TOP-1 accuracy, and the precision, sensitivity, specificity, and F1 score of each model are calculated, and receiver operating characteristic (ROC) curves are plotted to evaluate the model performance. Gradient-weighted class activation mapping (Grad-CAM) images are used to determine the image features that are most important for DCNN decisions. A total of 1378 (80%) images were used for model development, and model efficacy was validated on a test set with 343 (20%) images. The overall TOP-1 accuracy was 98.5%. The area under the receiver operating characteristic curve (AUC) values for each internal fixation model were 1.000, 1.000, 0.980, 1.000, 0.999, and 1.000, respectively. Gradient-weighted class activation mapping showed the unique design of the internal fixation device. We developed a deep convolutional neural network model that can identify the manufacturer and model of hip internal fixation devices from the hip AP radiographs.
Identifiants
pubmed: 36964792
doi: 10.1007/s00256-023-04324-5
pii: 10.1007/s00256-023-04324-5
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1577-1583Informations de copyright
© 2023. The Author(s), under exclusive licence to International Skeletal Society (ISS).
Références
Kanis JA, Odén A, McCloskey EV, et al. A systematic review of hip fracture incidence and probability of fracture worldwide. Osteoporos Int. 2012;23:2239–56. https://doi.org/10.1007/s00198-012-1964-3 .
doi: 10.1007/s00198-012-1964-3
pubmed: 22419370
pmcid: 3421108
Cummings SR, Melton LJ. Epidemiology and outcomes of osteoporotic fractures. The Lancet. 2002;359:1761–7. https://doi.org/10.1016/S0140-6736(02)08657-9 .
doi: 10.1016/S0140-6736(02)08657-9
Cooper C, Campion G, Melton LJ. Hip fractures in the elderly: a world-wide projection. Osteoporosis Int. 1992;2:285–9. https://doi.org/10.1007/BF01623184 .
doi: 10.1007/BF01623184
The IOF CSA Working Group on Fracture Epidemiology, Cooper C, Cole ZA, et al. Secular trends in the incidence of hip and other osteoporotic fractures. Osteoporos Int. 2011;22:1277–88. https://doi.org/10.1007/s00198-011-1601-6 .
doi: 10.1007/s00198-011-1601-6
pmcid: 3546313
Recommendations | Hip fracture: management | Guidance | NICE. https://www.nice.org.uk/guidance/cg124/chapter/Recommendations . Accessed 20 Sep 2022
Khan SK, Kalra S, Khanna A, et al. Timing of surgery for hip fractures: a systematic review of 52 published studies involving 291,413 patients. Injury. 2009;40:692–7. https://doi.org/10.1016/j.injury.2009.01.010 .
doi: 10.1016/j.injury.2009.01.010
pubmed: 19450802
Lin JC-F, Liang W-M. Mortality, readmission, and reoperation after hip fracture in nonagenarians. BMC Musculoskelet Disord. 2017;18:144. https://doi.org/10.1186/s12891-017-1493-5 .
doi: 10.1186/s12891-017-1493-5
pubmed: 28376876
pmcid: 5381150
Wilson N, Broatch J, Jehn M, Davis C. National projections of time, cost and failure in implantable device identification: consideration of unique device identification use. Healthcare. 2015;3:196–201. https://doi.org/10.1016/j.hjdsi.2015.04.003 .
doi: 10.1016/j.hjdsi.2015.04.003
pubmed: 26699343
Health C for D and R. Unique Device Identification System (UDI System). In: FDA. 2022. https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system . Accessed 20 Sep 2022
Jiang Y, Yang M, Wang S, et al. Emerging role of deep learning-based artificial intelligence in tumor pathology. Cancer Commun. 2020;40:154–66. https://doi.org/10.1002/cac2.12012 .
doi: 10.1002/cac2.12012
Schwalbe N, Wahl B. Artificial intelligence and the future of global health. Lancet. 2020;395:1579–86. https://doi.org/10.1016/S0140-6736(20)30226-9 .
doi: 10.1016/S0140-6736(20)30226-9
pubmed: 32416782
pmcid: 7255280
Yoon AP, Lee Y-L, Kane RL, et al. Development and validation of a deep learning model using convolutional neural networks to identify scaphoid fractures in radiographs. JAMA Netw Open 4:e216096. https://doi.org/10.1001/jamanetworkopen.2021.6096 .
Ting DSW, Cheung CY-L, Lim G, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017;318:2211–23. https://doi.org/10.1001/jama.2017.18152 .
doi: 10.1001/jama.2017.18152
pubmed: 29234807
pmcid: 5820739
Milea D, Najjar RP, Jiang Z, et al. Artificial intelligence to detect papilledema from ocular fundus photographs. N Engl J Med. 2020;382:1687–95. https://doi.org/10.1056/NEJMoa1917130 .
doi: 10.1056/NEJMoa1917130
pubmed: 32286748
Borjali A, Chen AF, Bedair HS, et al. Comparing the performance of a deep convolutional neural network with orthopedic surgeons on the identification of total hip prosthesis design from plain radiographs. Med Phys. 2021;48:2327–36. https://doi.org/10.1002/mp.14705 .
doi: 10.1002/mp.14705
pubmed: 33411949
Tan M, Le QV. EfficientNet: rethinking model scaling for convolutional neural networks [Internet]. arXiv:1905.11946. 2020 [cited 2023 Mar 10]. Available from: http://arxiv.org/abs/1905.11946 .
Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115:211–52. https://doi.org/10.1007/s11263-015-0816-y .
doi: 10.1007/s11263-015-0816-y
Selvaraju RR, Cogswell M, Das A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE; 2017. p. 618–26. https://doi.org/10.1109/ICCV.2017.74 .
Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017;69S:S36–40. https://doi.org/10.1016/j.metabol.2017.01.011 .
doi: 10.1016/j.metabol.2017.01.011
pubmed: 28126242
Ozkaya E, Topal FE, Bulut T, et al. Evaluation of an artificial intelligence system for diagnosing scaphoid fracture on direct radiography. Eur J Trauma Emerg Surg. 2022;48:585–92. https://doi.org/10.1007/s00068-020-01468-0 .
doi: 10.1007/s00068-020-01468-0
pubmed: 32862314
Karnuta JM, Haeberle HS, Luu BC, et al. Artificial intelligence to identify arthroplasty implants from radiographs of the hip. J Arthroplasty. 2021;36:S290-S294.e1. https://doi.org/10.1016/j.arth.2020.11.015 .
doi: 10.1016/j.arth.2020.11.015
pubmed: 33281020
Yi PH, Wei J, Kim TK, et al. Automated detection & classification of knee arthroplasty using deep learning. Knee. 2020;27:535–42. https://doi.org/10.1016/j.knee.2019.11.020 .
doi: 10.1016/j.knee.2019.11.020
pubmed: 31883760