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
Unstable pelvic injuries in young children with
an immature pelvis have different modes of failure from those in adolescents
and adults. We describe the
It has previously been suggested that among unstable
ankle fractures, the presence of a malleolar fracture is associated
with a worse outcome than a corresponding ligamentous injury. However,
previous studies have included heterogeneous groups of injury. The
purpose of this study was to determine whether any specific pattern of
bony and/or ligamentous injury among a series of supination-external
rotation type IV (SER IV) ankle fractures treated with anatomical
fixation was associated with a worse outcome. We analysed a prospective cohort of 108 SER IV ankle fractures
with a follow-up of one year. Pre-operative radiographs and MRIs
were undertaken to characterise precisely the pattern of injury.
Operative treatment included fixation of all malleolar fractures.
Post-operative CT was used to assess reduction. The primary and
secondary outcome measures were the Foot and Ankle Outcome Score
(FAOS) and the range of movement of the ankle. There were no clinically relevant differences between the four
possible SER IV fracture pattern groups with regard to the FAOS
or range of movement. In this population of strictly defined SER
IV ankle injuries, the presence of a malleolar fracture was not
associated with a significantly worse clinical outcome than its
ligamentous injury counterpart. Other factors inherent to the injury
and treatment may play a more important role in predicting outcome.
We carried out a retrospective review of 47 intra-articular fractures of the calcaneum treated by open reduction and internal fixation in 45 patients by a single surgeon between 1993 and 2001. The fractures were evaluated before operation by plain radiographs and a CT scan using Sanders’ classification. Osteosynthesis involved a lateral approach and the use of the AO calcaneal plate. The mean follow-up was for ten years (7 to 15). Clinical assessment included the American Orthopaedic Foot and Ankle Society Score (AOFAS), the Creighton-Nebraska Score, the Kerr, Prothero, Atkins Score and the SF-36 Health Questionnaire. The radiological evaluation consisted of lateral and axial views of the os calcis. Arthritic changes in the subtalar joint were assessed with an internal oblique view and were graded using the Morrey and Wiedeman scale. There were 18 excellent (38.3%), 17 good (36.2%), three fair (6.3%) and nine poor (19.2%) results. Five patients had a superficial wound infection and five others eventually had a subtalar arthrodesis because of continuing pain. Restoration of Böhler’s angle was associated with a better outcome. The degree of arthritic change in the subtalar joint did not correlate with the outcome scores or Sanders’ classification. Prompt osteosynthesis should be considered for intra-articular fractures of the calcaneum in order to restore the shape of the hindfoot and Böhler’s angle.