The aim of this study was to develop and evaluate a deep learning-based model for classification of hip fractures to enhance diagnostic accuracy. A retrospective study used 5,168 hip anteroposterior radiographs, with 4,493 radiographs from two institutes (internal dataset) for training and 675 radiographs from another institute for validation. A convolutional neural network (CNN)-based classification model was trained on four types of hip fractures (Displaced, Valgus-impacted, Stable, and Unstable), using DAMO-YOLO for data processing and augmentation. The model’s accuracy, sensitivity, specificity, Intersection over Union (IoU), and Dice coefficient were evaluated. Orthopaedic surgeons’ diagnoses served as the reference standard, with comparisons made before and after artificial intelligence assistance.Aims
Methods
No randomized comparative study has compared the extensile lateral approach (ELA) and sinus tarsi approach (STA) for Sanders type 2 calcaneal fractures. This randomized comparative study was conducted to confirm whether the STA was prone to fewer wound complications than the ELA. Between August 2013 and August 2018, 64 patients with Sanders type 2 calcaneus fractures were randomly assigned to receive surgical treatment by the ELA (32 patients) and STA (32 patients). The primary outcome was development of wound complications. The secondary outcomes were postoperative complications, pain scored of a visual analogue scale (VAS), American Orthopaedic Foot and Ankle Society (AOFAS) score, 36-item Short Form health survey, operative duration, subtalar joint range of motion (ROM), Böhler’s angle and calcaneal width, and posterior facet reduction.Aims
Methods
