Application of deep learning algorithm in automated identification of knee arthroplasty implants from plain radiographs using transfer learning models: Are algorithms better than humans?

Tiwari, Anjali; Yadav, Amit Kumar; Bagaria, Vaibhav

doi:10.1016/j.jor.2022.05.013

Cited by 10 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sharma et al [19] have classified six implant types using 1078 images and compared four different networks with an external test set that consists of 162 images. Tiwari et al [9] have classified six implant types using 521 images, and they have shown the superiority of ML models over human experts regarding the average accuracy. Patel et al [10] have used both knee and hip radiographs, identifying 12 implant types using 427 knee and 922 hip unilateral images.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Detection of Surgical Implants on Plain Knee Radiographs Using a Deep Learning Algorithm

Kim

Lee

et al. 2022

Medicina

View full text Add to dashboard Cite

Background and Objectives: The number of patients who undergo multiple operations on a knee is increasing. The objective of this study was to develop a deep learning algorithm that could detect 17 different surgical implants on plain knee radiographs. Materials and Methods: An internal dataset consisted of 5206 plain knee antero-posterior X-rays from a single, tertiary institute for model development. An external set contained 238 X-rays from another tertiary institute. A total of 17 different types of implants including total knee arthroplasty, unicompartmental knee arthroplasty, plate, and screw were labeled. The internal dataset was approximately split into a train set, a validation set, and an internal test set at a ratio of 7:1:2. You Only look Once (YOLO) was selected as the detection network. Model performances with the validation set, internal test set, and external test set were compared. Results: Total accuracy, total sensitivity, total specificity value of the validation set, internal test set, and external test set were (0.978, 0.768, 0.999), (0.953, 0.810, 0.990), and (0.956, 0.493, 0.975), respectively. Means ± standard deviations (SDs) of diagonal components of confusion matrix for these three subsets were 0.858 ± 0.242, 0.852 ± 0.182, and 0.576 ± 0.312, respectively. True positive rate of total knee arthroplasty, the most dominant class of the dataset, was higher than 0.99 with internal subsets and 0.96 with an external test set. Conclusion: Implant identification on plain knee radiographs could be automated using a deep learning technique. The detection algorithm dealt with overlapping cases while maintaining high accuracy on total knee arthroplasty. This could be applied in future research that analyzes X-ray images with deep learning, which would help prompt decision-making in clinics.

show abstract

Section: Discussionmentioning

confidence: 99%

“…DL model could significantly reduce time and cost spent in identifying implants by examining X-ray images directly and automatically. Tiwari et al [9] and Patel et al [10] have directly compared DL models with human experts in examining X-ray images and proven that DL models are better in both speed and accuracy.…”

Section: Introductionmentioning

confidence: 99%

Automated Detection of Surgical Implants on Plain Knee Radiographs Using a Deep Learning Algorithm

Kim

Lee

et al. 2022

Medicina

View full text Add to dashboard Cite

show abstract

“…The identification of the brand of knee arthroplasty prosthesis is very important for planning a revision knee arthroplasty. However, it takes a lot of time and effort to determine the implant brand from a primary knee arthroplasty [1]. The frequency of patients having repeated knee surgeries is rising along with the number of knee operations being performed [2].…”

Section: Introductionmentioning

confidence: 99%

Identification of Knee Prostheses from Lateral Radiographs Using Deep Learning Techniques

Bagewadi,

et al. 2023

World Congress on Electrical Engineering and Computer Systems and Science

View full text Add to dashboard Cite

The field of medical imaging has seen significant progress in recent years, particularly with the evolution of deep learning techniques. In the context of arthroplasty, the ability to accurately detect and identify specific implant models is crucial for proper patient care and revision surgery. However, manual identification of implants from radiographic images (X-Ray) takes a lot of time and is affected by manual human error. To solve this, this research proposes a deep learning-based novel approach to automate the identification of Knee arthroplasty implants from Lateral (LAT) view X-ray images of the implant. Pre trained convolutional neural networks are used for this purpose. Best results are obtained using VGG16 which produces a higher accuracy of 81.61% and stronger Area Under Curve (AUC) of 0.9547.

show abstract

Artificial Intelligence, Deep Learning, and Machine Learning Applications in Total Knee Arthroplasty

Sosa

2023

Total Knee Arthroplasty

View full text Add to dashboard Cite

Application of deep learning algorithm in automated identification of knee arthroplasty implants from plain radiographs using transfer learning models: Are algorithms better than humans?

Cited by 10 publications

References 20 publications

Automated Detection of Surgical Implants on Plain Knee Radiographs Using a Deep Learning Algorithm

Automated Detection of Surgical Implants on Plain Knee Radiographs Using a Deep Learning Algorithm

Identification of Knee Prostheses from Lateral Radiographs Using Deep Learning Techniques

Artificial Intelligence, Deep Learning, and Machine Learning Applications in Total Knee Arthroplasty

Contact Info

Product

Resources

About