The aim of this study was to create artificial intelligence (AI) software with the purpose of providing a second opinion to physicians to support distal radius fracture (DRF) detection, and to compare the accuracy of fracture detection of physicians with and without software support. The dataset consisted of 26,121 anonymized anterior-posterior (AP) and lateral standard view radiographs of the wrist, with and without DRF. The convolutional neural network (CNN) model was trained to detect the presence of a DRF by comparing the radiographs containing a fracture to the inconspicuous ones. A total of 11 physicians (six surgeons in training and five hand surgeons) assessed 200 pairs of randomly selected digital radiographs of the wrist (AP and lateral) for the presence of a DRF. The same images were first evaluated without, and then with, the support of the CNN model, and the diagnostic accuracy of the two methods was compared.Aims
Methods
Ununited fractures of the scaphoid with extensive bone resorption are usually treated by bone grafting and internal fixation, using either an open or a minimally invasive technique. We studied the feasibility of percutaneous fixation without bone grafting in a consecutive series of 27 patients with established nonunion of an undisplaced fracture of the scaphoid and extensive local resorption of bone. They were treated by a single surgeon with rigid fixation alone, using a headless cannulated screw inserted through a volar percutaneous technique. Clinical examination, standard radiographs and CT confirmed that the fracture had united in all patients at a mean of 11.6 weeks (8 to 16), and that their functional scores had improved. We concluded that extensive resorption at the fracture site is not an absolute indication for bone grafting, and that percutaneous fixation alone will eventually produce healing of ununited undisplaced fractures of the scaphoid regardless of the size of the gap.
