Utilizing “You only look once” (YOLO) v4 AI offers valuable support in fracture detection and diagnostic decision-making. The purpose of this study was to help doctors to detect and diagnose fractures more accurately and intuitively, with fewer errors. The data accepted into the backbone are diversified through CSPDarkNet-53. Feature maps are extracted using Spatial Pyramid Pooling and a Path Aggregation Network in the neck part. The head part aggregates and generates the final output. All bounding boxes by the YOLO v4 are mapped onto the 3D reconstructed bone images after being resized to match the same region as shown in the 2D CT images. The YOLO v4-based AI model was evaluated through precision–recall (PR) curves and the intersection over union (IoU). Our proposed system facilitated an intuitive display of the fractured area through a distinctive red mask overlaid on the 3D reconstructed bone images. The high average precision values (>0.60) were reported as 0.71 and 0.81 from the PR curves of the tibia and elbow, respectively. The IoU values were calculated as 0.6327 (tibia) and 0.6638 (elbow). When utilized by orthopedic surgeons in real clinical scenarios, this AI-powered 3D diagnosis support system could enable a quick and accurate trauma diagnosis.

Background: There is limited information regarding the long-term efficacy of techniques for surgical fixation after acromioclavicular (AC) joint dislocation. Purpose: To evaluate the efficacy of hook plate (HP) and TightRope (TR) fixation for acute AC joint dislocations by comparing the long-term clinical and radiological patient outcomes. Study Design: Cohort study, Level of evidence, 3. Methods: This study retrospectively analyzed data from 61 patients with acute AC joint dislocation between July 2011 and November 2015. The patients were grouped according to surgical procedure: HP (n = 36) and TR (n = 25). Clinical outcomes at final follow-up were evaluated using the visual analog scale (VAS) for pain; the American Shoulder and Elbow Surgery score; the Korean Shoulder Score; and the University of California, Los Angeles (UCLA) shoulder score. Side-to-side coracoclavicular (CC) distance on radiographs, postoperative complications, and the rate of subacromial erosion in the HP group were also assessed between procedures. Results: The mean follow-up period was 7.0 ± 1.0 years, and there were no significant differences in pain or outcome scores between the HP and TR groups (all P > .05). Forward flexion was better in the TR group (172.6° ± 5.6°) versus the HP group (166.0° ± 10.8°; P = .002). The percentages of patients with a difference in the side-to-side CC distance of <5 mm were 83.3% and 72.0% in the HP and TR groups, respectively ( P = .288). Complications were found in 2 patients in the HP group and 1 in the TR group ( P ≥ .999). Subacromial erosion was observed in 41.7% of patients after HP fixation, with no difference in VAS pain scores at the final follow-up in patients with versus without subacromial erosion ( P = .719). Conclusion: When comparing HP with TR fixation for the treatment of acute AC joint dislocations, there were no significant differences in functional outcome scores, final CC distance, or complications. Slightly better forward flexion was seen after TR fixation. Subacromial erosion occurred in 40% of patients after HP fixation, but this did not affect long-term VAS pain scores. Both surgical techniques are effective treatment options for AC joint dislocation.

If reduction images of fractures can be provided in advance with artificial-intelligence (AI)-based technology, it can assist with preoperative surgical planning. Recently, we developed the AI-based preoperative virtual reduction model for orthopedic trauma, which can provide an automatic segmentation and reduction of fractured fragments. The purpose of this study was to validate a quality of reduction model of Neer 3- or 4-part proximal humerus fractures established by AI-based technology. To develop the AI-based preoperative virtual reduction model, deep learning performed the segmentation of fracture fragments, and a Monte Carlo simulation completed the virtual reduction to determine the best model. A total of 20 pre/postoperative three-dimensional computed tomography (CT) scans of proximal humerus fracture were prepared. The preoperative CT scans were employed as the input of AI-based automated reduction (AI-R) to deduce the reduction models of fracture fragments, meanwhile, the manual reduction (MR) was conducted using the same CT images. Dice similarity coefficient (DSC) and intersection over union (IoU) between the reduction model from the AI-R/MR and postoperative CT scans were evaluated. Working times were compared between the two groups. Clinical validity agreement (CVA) and reduction quality score (RQS) were investigated for clinical validation outcomes by 20 orthopedic surgeons. The mean DSC and IoU were better when using AI-R that when using MR (0.78 ± 0.13 vs. 0.69 ± 0.16, p < 0.001 and 0.65 ± 0.16 vs. 0.55 ± 0.18, p < 0.001, respectively). The working time of AI-R was, on average, 1.41% of that of MR. The mean CVA of all cases was 81%±14.7% (AI-R, 82.25%±14.27%; MR, 76.75%±14.17%, p = 0.06). The mean RQS was significantly higher when AI-R compared with MR was used (91.47 ± 1.12 vs. 89.30 ± 1.62, p = 0.045). The AI-based preoperative virtual reduction model showed good performance in the reduction model in proximal humerus fractures with faster working times. Beyond diagnosis, classification, and outcome prediction, the AI-based technology can change the paradigm of preoperative surgical planning in orthopedic surgery. Level IV.

Background: The aim of this study was to evaluate clinical experience with arthroscopic debridement for septic arthritis of the shoulder joint and to report on our patient outcomes.Methods: The retrospective analysis included 36 shoulders (male:female, 15:21), contributed by 35 patients (mean age, 63.8 years) treated by arthroscopy for septic arthritis of the shoulder between November 2003 and February 2016. The mean follow-up period was 14.3 months (range, 12–33 months). An additional posterolateral portal and a 70º arthroscope was used to access the posteroinferior glenohumeral (GH) joint and posteroinferior subacromial (SA) space, respectively. Irrigation was performed with a large volume of fluid (25.1±8.1 L). Multiple suction drains (average, 3.3 drains) were inserted into the GH joint and SA space and removed 8.9±4.3 days after surgery. Intravenous antibiotics were administered for 3.9±1.8 weeks after surgery, followed by oral antibiotic treatment for another 3.6±1.9 weeks.Results: Among the 36 shoulders, reoperation was required in two cases (5.6%). The average range of motion achieved was 150.0º for forward flexion and T9 for internal rotation. The mean simple shoulder test score was 7.9±3.6 points. Nineteen shoulders (52.8%) had acupuncture or injection history prior to the infection. Pathogens were identified in 15 shoulders, with Staphylococcus aureus being the most commonly identified pathogen (10/15). Both the GH joint and the SA space were involved in 21 shoulders, while 14 cases involved only the GH joint and one case involved only the SA space. Conclusions: Complete debridement using an additional posterolateral portal and 70º arthroscope, a large volume of irrigation with >20 L of saline, and multiple suction drains may reduce the reoperation rate.