Advertisement for orthosearch.org.uk
Results 1 - 2 of 2
Results per page:
Orthopaedic Proceedings
Vol. 105-B, Issue SUPP_2 | Pages 102 - 102
10 Feb 2023
White J Wadhawan A Min H Rabi Y Schmutz B Dowling J Tchernegovski A Bourgeat P Tetsworth K Fripp J Mitchell G Hacking C Williamson F Schuetz M
Full Access

Distal radius fractures (DRFs) are one of the most common types of fracture and one which is often treated surgically. Standard X-rays are obtained for DRFs, and in most cases that have an intra-articular component, a routine CT is also performed. However, it is estimated that CT is only required in 20% of cases and therefore routine CT's results in the overutilisation of resources burdening radiology and emergency departments. In this study, we explore the feasibility of using deep learning to differentiate intra- and extra-articular DRFs automatically and help streamline which fractures require a CT.

Retrospectively x-ray images were retrieved from 615 DRF patients who were treated with an ORIF at the Royal Brisbane and Women's Hospital. The images were classified into AO Type A, B or C fractures by three training registrars supervised by a consultant. Deep learning was utilised in a two-stage process: 1) localise and focus the region of interest around the wrist using the YOLOv5 object detection network and 2) classify the fracture using a EfficientNet-B3 network to differentiate intra- and extra-articular fractures.

The distal radius region of interest (ROI) detection stage using the ensemble model of YOLO networks detected all ROIs on the test set with no false positives. The average intersection over union between the YOLO detections and the ROI ground truth was Error! Digit expected.. The DRF classification stage using the EfficientNet-B3 ensemble achieved an area under the receiver operating characteristic curve of 0.82 for differentiating intra-articular fractures.

The proposed DRF classification framework using ensemble models of YOLO and EfficientNet achieved satisfactory performance in intra- and extra-articular fracture classification. This work demonstrates the potential in automatic fracture characterization using deep learning and can serve to streamline decision making for axial imaging helping to reduce unnecessary CT scans.


Orthopaedic Proceedings
Vol. 94-B, Issue SUPP_XXXIV | Pages 16 - 16
1 Jul 2012
White J Ahir S Hua J
Full Access

Hip resurfacing arthroplasty is emerging as an increasingly popular, conservative option for the treatment of end-stage osteoarthritis in the young and active patient. Despite the encouraging clinical results of hip resurfacing, aseptic loosening and femoral neck fracture remains concerns for the success of this procedure.

This study used finite element analysis (FEA) to analyse the stresses within proximal femoral bone resulting from implantation with a conservative hip prosthesis. FEA is a computational method used to analyse the performance of real-world structures through the development of simplified computational models using essential features.

The aim of this study was to examine the correlation between the orientation of the femoral component of a hip resurfacing prosthesis (using the Birmingham Hip Resurfacing as a model) and outcomes during both walking and stair climbing. The outcomes of interest were stresses in the femoral neck predisposing to fracture, and bone remodelling within the proximal femur.

Multiple three-dimensional finite element models of a resurfaced femur were generated, with stem-shaft angles representing anatomic (135°), valgus (145°), and varus (125°) angulations. Applied loading conditions included normal walking and stair climbing. Bone remodelling was assessed in both the medial and lateral cortices.

Analyses revealed that amongst all orientations, valgus positioning produced the most physiological stress patterns within these regions, thereby encouraging bone growth. Stress concentration was observed in cortical and cancellous bone regions adjacent to the rim of the prosthesis. As one would expect, stair climbing produced consistently higher stress than walking. The highest stress values occurred in the varus-orientated femur during both walking and stair climbing, whilst anatomic angulation resulted in the lowest stress values of all implanted femurs in comparison to the intact femur.

This study has shown through the use of FEA that optimising the stem-shaft angle towards a valgus orientation is recommended when implanting a hip resurfacing arthroplasty. This positioning produces physiological stress patterns within the proximal femur that are conducive to bone growth, thus reducing the risk of femoral neck fracture associated with conservative hip arthroplasty.