journal article Open Access Nov 19, 2022

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

Medicina Vol. 58 No. 11 pp. 1677 · MDPI AG
View at Publisher Save 10.3390/medicina58111677
Abstract
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.
Topics

No keywords indexed for this article. Browse by subject →

References
23
[1]
Postler, A., Lützner, C., Beyer, F., Tille, E., and Lützner, J. (2018). Analysis of total knee arthroplasty revision causes. BMC Musculoskelet. Disord., 19. 10.1186/s12891-018-1977-y
[2]
Sun "A meta-analysis of total knee arthroplasty following high tibial osteotomy versus primary total knee arthroplasty" Arch. Orthop. Trauma Surg. (2020) 10.1007/s00402-020-03333-6
[3]
MacDonald "Preoperative evaluations in revision total knee arthroplasty" Clin. Orthop. Relat. Res. (2006) 10.1097/01.blo.0000218727.14097.d5
[4]
Dy "Is changing hospitals for revision total joint arthroplasty associated with more complications?" Clin. Orthop. Relat. Res. (2014) 10.1007/s11999-014-3515-z
[5]
Wilson "Revision total hip and knee arthroplasty implant identification: Implications for use of unique device identification 2012 AAHKS member survey results" J. Arthroplast. (2014) 10.1016/j.arth.2013.06.027
[6]
"Machine learning approaches in medical image analysis: From detection to diagnosis" Med. Image Anal. (2016) 10.1016/j.media.2016.06.032
[7]
Madabhushi "Image analysis and machine learning in digital pathology: Challenges and opportunities" Med. Image Anal. (2016) 10.1016/j.media.2016.06.037
[8]
Deep Learning in Medical Image Analysis

Dinggang Shen, Guorong Wu, Heung-Il Suk

Annual Review of Biomedical Engineering 2017 10.1146/annurev-bioeng-071516-044442
[9]
Tiwari "Application of deep learning algorithm in automated identification of knee arthroplasty implants from plain radiographs using transfer learning models: Are algorithms better than humans?" J. Orthop. (2022) 10.1016/j.jor.2022.05.013
[10]
Patel "Automated identification of orthopedic implants on radiographs using deep learning" Radiol. Artif. Intell. (2021) 10.1148/ryai.2021200183
[11]
Ren "Artificial intelligence in orthopedic implant model classification: A systematic review" Skelet. Radiol. (2021) 10.1007/s00256-021-03884-8
[12]
Paul "Automated detection & classification of knee arthroplasty using deep learning" Knee (2020) 10.1016/j.knee.2019.11.020
[13]
Karnuta "Artificial intelligence to identify arthroplasty implants from radiographs of the knee" J. Arthroplast. (2021) 10.1016/j.arth.2020.10.021
[14]
You Only Look Once: Unified, Real-Time Object Detection

Joseph Redmon, Santosh Divvala, Ross Girshick et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.91
[15]
(2020, May 18). COCO—Common Objects in Context. Available online: https://cocodataset.org/#home.
[16]
(2020, May 18). YOLOv5 Documentation. Augmentation—YOLOv5 Documentation. Available online: https://docs.ultralytics.com/FAQ/augmentation/.
[17]
YOLOv5 (2020, May 18). yolov5/datasets.py. Available online: https://github.com/ultralytics/yolov5/blob/90b7895d652c3bd3d361b2d6e9aee900fd67f5f7/utils/datasets.py#L678-L732.
[18]
Belete "Automated classification of total knee replacement prosthesis on plain film radiograph using a deep convolutional neural network" Inform. Med. Unlocked (2021) 10.1016/j.imu.2021.100669
[19]
Sharma "Knee Implant Identification by Fine-Tuning Deep Learning Models" Indian J. Orthop. (2021) 10.1007/s43465-021-00529-9
[20]
Klemt "The Ability of Deep Learning Models to Identify Total Hip and Knee Arthroplasty Implant Design From Plain Radiographs" J. Am. Acad. Orthop. Surg. (2020)
[21]
Gurung "Artificial intelligence for image analysis in total hip and total knee arthroplasty: A scoping review" Bone Jt. J. (2022) 10.1302/0301-620x.104b8.bjj-2022-0120.r2
[22]
Kang "Machine learning–based identification of hip arthroplasty designs" J. Orthop. Transl. (2020)
[23]
Urban "Classifying shoulder implants in X-ray images using deep learning" Comput. Struct. Biotechnol. J. (2020) 10.1016/j.csbj.2020.04.005
Metrics
12
Citations
23
References
Details
Published
Nov 19, 2022
Vol/Issue
58(11)
Pages
1677
License
View
Cite This Article
Back Kim, Do Weon Lee, Sanggyu Lee, et al. (2022). Automated Detection of Surgical Implants on Plain Knee Radiographs Using a Deep Learning Algorithm. Medicina, 58(11), 1677. https://doi.org/10.3390/medicina58111677