Aims. 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. Methods. 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%). Results. For detection and classification, the algorithm was trained on 1,709 radiographs (n = 803), tested on 567 radiographs (n = 244), and subsequently externally validated on 535 radiographs (n = 227). For characterization, healthy shoulders and glenohumeral dislocation were excluded. The overall accuracy for fracture detection was 94% (area under the receiver operating characteristic curve (AUC) = 0.98) and for classification 78% (AUC 0.68 to 0.93). Accuracy to detect greater tuberosity fracture displacement ≥ 1 cm was 35.0% (AUC 0.57). The CNN did not recognize NSAs ≤ 100° (AUC 0.42), nor fractures with ≥ 75% shaft translation (AUC 0.51 to 0.53), or with ≥ 15% articular involvement (AUC 0.48 to 0.49). For all objectives, the model’s performance on the external dataset showed similar accuracy levels. Conclusion. CNNs proficiently rule out proximal humerus fractures on plain radiographs. Despite rigorous training methodology based on CT imaging with multi-rater consensus to serve as the reference standard, artificial intelligence-driven classification is insufficient for clinical implementation. The CNN exhibited poor diagnostic ability to detect greater tuberosity displacement ≥ 1 cm and failed to identify NSAs ≤ 100°, shaft translations, or articular fractures. Cite this article: Bone Joint J 2024;106-B(11):1348–1360

Aims

To evaluate whether an ultra-low-dose CT protocol can diagnose selected limb fractures as well as conventional CT (C-CT).

The incidence and long-term outcome of undisplaced fatigue fractures of the femoral neck treated conservatively were examined in Finnish military conscripts between 1970 and 1990.

From 106 cases identified, 66 patients with 70 fractures were followed for a mean of 18.3 years (11 to 32). The original medical records and radiographs were studied and physical and radiological follow-up data analysed for evidence of risk factors for this injury. The development of avascular necrosis and osteoarthritis was determined from the follow-up radiographs and MR scans.

The impact of new military instructions on the management of hip-related pain was assessed following their introduction in 1986. The preventive regimen (1986) improved awareness and increased the detected incidence from 13.2 per 100 000 service-years (1970 to 1986) to 53.2 per 100 000 (1987 to 1990). No patient developed displacement of the fracture or avascular necrosis of the femoral head, or suffered from adverse complications. No differences were found in MRI-measured hip joint spaces at final follow-up. The mean Harris Hip Score was 97 (70 to 100) and the Visual Analogue Scale 5.85 mm (0 to 44).

Non-operative treatment, including avoidance of or reduced weight-bearing, gave favourable short- and long-term outcomes. Undisplaced fatigue fractures of the femoral neck neither predispose to avascular necrosis nor the subsequent development of osteoarthritis of the hip.