Introduction. With advances in artificial intelligence, the use of computer-aided detection and diagnosis in clinical imaging is gaining traction. Typically, very large datasets are required to train machine-learning models, potentially limiting use of this technology when only small datasets are available. This study investigated whether pretraining of fracture detection models on large, existing datasets could improve the performance of the model when locating and classifying wrist fractures in a small X-ray image dataset. This concept is termed “transfer learning”. Method. Firstly, three detection models, namely, the faster region-based convolutional neural network (faster R-CNN), you only look once version eight (YOLOv8), and RetinaNet, were pretrained using the large, freely available dataset, common objects in context (COCO) (330000 images). Secondly, these models were pretrained using an open-source wrist X-ray dataset called “Graz Paediatric Wrist Digital X-rays” (GRAZPEDWRI-DX) on a (1) fracture detection dataset (20327 images) and (2) fracture location and classification dataset (14390 images). An orthopaedic surgeon classified the small available dataset of 776 distal radius X-rays (Arbeidsgmeischaft für Osteosynthesefragen Foundation / Orthopaedic Trauma Association; AO/OTA), on which the models were tested. Result. Detection models without pre-training on the large datasets were the least precise when tested on the small distal radius dataset. The model with the best accuracy to detect and classify wrist fractures was the YOLOv8 model pretrained on the GRAZPEDWRI-DX fracture detection dataset (mean average precision at intersection over union of 50=59.7%). This model showed up to 33.6% improved detection precision compared to the same models with no pre-training. Conclusion. Optimisation of machine-learning models can be challenging when only relatively small datasets are available. The findings of this study support the potential of transfer learning from large datasets to improve model performance in smaller datasets. This is encouraging for wider application of machine-learning technology in medical imaging evaluation, including less common orthopaedic pathologies

We assessed carpal collapse by measuring the capitate-radius (CR) distance on standard plain radiographs. This new method required validation of diagnostic accuracy, so we compared it with the method of Nattrass et al. 1. known as revised carpal height (RCH). We studied wrist radiographs from 16 normal subjects and 11 patients with unilateral Kienböck’s disease. We found that there was a significant difference in the left/right CR index between the normal wrists and those with Kienböck’s disease (p < 0.001). The use of left/right RCH index showed no significant difference (p = 0.30). Diagnostic accuracy was shown to be higher for the CR index using ROC curves. We then assessed 40 normal wrists and found the mean CR index to be 0.999 ± 0.034, and suggest that values less than 0.92 are abnormal. The CR index can be used for diagnosis in unilateral carpal collapse, and for monitoring progress where the condition is bilateral