The purpose of this study was to develop a convolutional neural network (CNN) for fracture detection, classification, and identification of greater tuberosity displacement ≥ 1 cm, neck-shaft angle (NSA) ≤ 100°, shaft translation, and articular fracture involvement, on plain radiographs. The CNN was trained and tested on radiographs sourced from 11 hospitals in Australia and externally validated on radiographs from the Netherlands. Each radiograph was paired with corresponding CT scans to serve as the reference standard based on dual independent evaluation by trained researchers and attending orthopaedic surgeons. Presence of a fracture, classification (non- to minimally displaced; two-part, multipart, and glenohumeral dislocation), and four characteristics were determined on 2D and 3D CT scans and subsequently allocated to each series of radiographs. Fracture characteristics included greater tuberosity displacement ≥ 1 cm, NSA ≤ 100°, shaft translation (0% to < 75%, 75% to 95%, > 95%), and the extent of articular involvement (0% to < 15%, 15% to 35%, or > 35%).Aims
Methods
Randomised controlled trials (RCTs) that assessed
the efficacy of bracing for adolescent idiopathic scoliosis have suffered
from small sample sizes, low compliance and lack of willingness
to participate. The aim of this study was to assess the feasibility
of a comprehensive cohort study for evaluating both the efficacy
and the effectiveness of bracing in patients with adolescent idiopathic
scoliosis. Patients with curves at greater risk of progression were invited
to join a randomised controlled trial. Those who declined were given
the option to remain in the study and to choose whether they wished
to be braced or observed. Of 87 eligible patients (5 boys and 63
girls) identified over one year, 68 (78%) with mean age of 12.5
years (10 to 15) consented to participate, with a mean follow-up
of 168 weeks (0 to 290). Of these, 19 (28%) accepted randomisation.
Of those who declined randomisation, 18 (37%) chose a brace. Patients
who were more satisfied with their image were more likely to choose
bracing (Odds Ratio 4.1; 95% confidence interval 1.1 to 15.0; p = 0.035).
This comprehensive cohort study design facilitates the assessment
of both efficacy and effectiveness of bracing in patients with adolescent
idiopathic scoliosis, which is not feasible in a conventional randomised
controlled trial. Cite this article:
