Imperial College London
Portrait Picture

Mr. Gareth G. Jones

Faculty of Medicine, Department of Surgery & Cancer

Clinical Senior Lecturer in Orthopaedic Surgery
 
 
 
//

Contact

 

+44 (0)20 7594 5465g.g.jones

 
 
//

Location

 

203Sir Michael Uren HubWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Burge:2022,
author = {Burge, T and Jones, G and Jordan, C and Jeffers, J and Myant, C},
journal = {Frontiers in Bioengineering and Biotechnology},
pages = {1--11},
title = {A computational tool for automatic selection of total knee replacementimplant size using x-ray images},
url = {https://www.frontiersin.org/articles/10.3389/fbioe.2022.971096/full},
volume = {10},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Purpose: The aim of this study was to outline a fully automatic tool capable of reliably predicting the most suitable total kneereplacement implant sizes for patients, using bi-planar X-ray images. By eliminating the need for manual templating or guidingsoftware tools via the adoption of convolutional neural networks, time and resource requirements for pre-operative assessmentand surgery could be reduced, the risk of human error minimized, and patients could see improved outcomes.Methods: The tool utilizes a machine learning-based 2D – 3D pipeline to generate accurate predictions of subjects’ distal femur andproximal tibia bones from X-ray images. It then virtually fits different implant models and sizes to the 3D predictions, calculatesthe implant to bone root-mean-squared error and maximum over/under hang for each, and advises the best option for thepatient. The tool was tested on 78, predominantly White subjects (45 female/33 male), using generic femur component and tibiaplate designs scaled to sizes obtained for five commercially available products. The predictions were then compared to the groundtruth best options, determined using subjects’ MRI data.Results: The tool achieved average femur component size prediction accuracies across the five implant models of 77.95% in termsof global fit (root-mean-squared error), and 71.79% for minimizing over/underhang. These increased to 99.74% and 99.49% with ±1size permitted. For tibia plates, the average prediction accuracies were 80.51% and 72.82% respectively. These increased to99.74% and 98.98% for ±1 size. Better prediction accuracies were obtained for implant models with fewer size options, howeversuch models more frequently resulted in a poor fit.Conclusion: A fully automatic tool was developed and found to enable higher prediction accuracies than generally reported formanual templating techniques, as well as similar computational methods.
AU  - Burge,T
AU  - Jones,G
AU  - Jordan,C
AU  - Jeffers,J
AU  - Myant,C
EP  - 11
PY  - 2022///
SN  - 2296-4185
SP  - 1
TI  - A computational tool for automatic selection of total knee replacementimplant size using x-ray images
T2  - Frontiers in Bioengineering and Biotechnology
UR  - https://www.frontiersin.org/articles/10.3389/fbioe.2022.971096/full
UR  - http://hdl.handle.net/10044/1/99483
VL  - 10
ER  -
Download