Summary
This study may lead to the development of an automated implant identification tool that could improve the accuracy and speed of decision made by healthcare professionals.
Abstract
Aim
In preoperative planning of a revision knee arthroplasty, it can be challenging to identify an implant manufacturer type from a primary knee arthroplasty due to the inability to identify the implants in time. It has been shown that deep learning improves diagnosis with each iteration in the medical field. The problem of identifying the manufacturer and model of knee arthroplasty prostheses has been solved using automated deep learning models. In our study, we have developed deep learning algorithm to identify knee arthroplasty, implant manufacturer type. The current study also aimed to determine the best of the seven machine learning-based model for detecting knee implants according to different manufacturing types from plain radiographs based on their efficacy and accuracy.
Material And Methods
Plain radiographs of 521 knee arthroplasty implants of six different manufacturers were taken from the anteroposterior and lateral perspectives to train, validate, and test the implants. Among 521 radiographs images, 70% were used in the initial training process, 10% in testing the models, and 20% in determining the accuracy and validity of the models. The study explored the transfer learning technique to develop models. The advantage of transfer learning for knee implant detection is that if existing models are already trained on a large enough and general dataset, these models can be used to fulfil the study's objectives. In addition, to establish the efficacy of these knee implants, two orthopaedic consultants specialised in arthroplasty independently identified these manufacturers types.
Results
The performance and network of the model resulted in high accuracy for identifying knee implant types out of seven models, five of which had more than 90% accuracy. After 20 training epochs on all seven models, based on the validation dataset, VGG-16 produces the best results with an accuracy of 95.5% and a precision of 98.4%. However, the study asserted that machine learning outperformed two human expert, who achieved an average accuracy of 78%.
Conclusion
This study may lead to the development of an automated implant identification tool that could improve the accuracy and speed of decision made by healthcare professionals.