Background and purpose — We aimed to evaluate the ability of artificial intelligence (a deep learning algorithm) to detect and classify proximal humerus fractures using plain anteroposterior shoulder radiographs.Patients and methods — 1,891 images (1 image per person) of normal shoulders (n = 515) and 4 proximal humerus fracture types (greater tuberosity, 346; surgical neck, 514; 3-part, 269; 4-part, 247) classified by 3 specialists were evaluated. We trained a deep convolutional neural network (CNN) after augmentation of a training dataset. The ability of the CNN, as measured by top-1 accuracy, area under receiver operating characteristics curve (AUC), sensitivity/specificity, and Youden index, in comparison with humans (28 general physicians, 11 general orthopedists, and 19 orthopedists specialized in the shoulder) to detect and classify proximal humerus fractures was evaluated.Results — The CNN showed a high performance of 96% top-1 accuracy, 1.00 AUC, 0.99/0.97 sensitivity/specificity, and 0.97 Youden index for distinguishing normal shoulders from proximal humerus fractures. In addition, the CNN showed promising results with 65–86% top-1 accuracy, 0.90–0.98 AUC, 0.88/0.83–0.97/0.94 sensitivity/specificity, and 0.71–0.90 Youden index for classifying fracture type. When compared with the human groups, the CNN showed superior performance to that of general physicians and orthopedists, similar performance to orthopedists specialized in the shoulder, and the superior performance of the CNN was more marked in complex 3- and 4-part fractures.Interpretation — The use of artificial intelligence can accurately detect and classify proximal humerus fractures on plain shoulder AP radiographs. Further studies are necessary to determine the feasibility of applying artificial intelligence in the clinic and whether its use could improve care and outcomes compared with current orthopedic assessments.
BackgroundIn the present study, we aimed to compare clinical and radiographic outcomes between hook plate fixation and coracoclavicular (CC) ligament reconstruction for the treatment of acute unstable acromioclavicular (AC) joint dislocation.MethodsForty-two patients who underwent surgery for an unstable acute dislocation of the AC joint were included. We divided them into two groups according to the treatment modality: internal fixation with a hook plate (group I, 24 cases) or CC ligament reconstruction (group II, 18 cases). We evaluated the clinical outcomes using a visual analog scale (VAS) for pain and Constant-Murley score, and assessed the radiographic outcomes based on the reduction and loss of CC distance on preoperative, postoperative, and final follow-up plain radiographs.ResultsThe mean VAS scores at the final follow-up were 1.6 ± 1.5 and 1.3 ± 1.3 in groups I and II, respectively, which were not significantly different. The mean Constant-Murley scores were 90.2 ± 9.9 and 89.2 ± 3.5 in groups I and II, respectively, which were also not significantly different. The AC joints were well reduced in both groups, whereas CC distance improved from a mean of 215.7% ± 50.9% preoperatively to 106.1% ± 10.2% at the final follow-up in group I, and from 239.9% ± 59.2% preoperatively to 133.6% ± 36.7% at the final follow-up in group II. The improvement in group I was significantly superior to that in group II (p < 0.001). Furthermore, subluxation was not observed in any case in group I, but was noted in six cases (33%) in group II. Erosions of the acromion undersurface were observed in 9 cases in group I.ConclusionsIn cases of acute unstable AC joint dislocation, hook plate fixation and CC ligament reconstruction yield comparable satisfactory clinical outcomes. However, radiographic outcomes based on the maintenance of reduction indicate that hook plate fixation is a better treatment option.
This study examined the role of vitamin D as a factor accounting for fatty degeneration and muscle function in the rotator cuff. There were 366 patients with disorders of the shoulder. A total of 228 patients had a full-thickness tear (group 1) and 138 patients had no tear (group 2). All underwent magnetic resonance arthrography and an isokinetic muscle performance test. The serum concentrations of vitamin D (25(OH)D(3)) were measured. In general, a lower serum level of vitamin D was related to higher fatty degeneration in the muscles of the cuff. Spearman's correlation coefficients were 0.173 (p = 0.001), -0.181 (p = 0.001), and -0.117 (p = 0.026) for supraspinatus, infraspinatus and subscapularis, respectively. In group 1, multivariate linear regression analysis revealed that the serum level of vitamin D was an independent variable for fatty degeneration of the supraspinatus and infraspinatus. The serum vitamin D level has a significant negative correlation with the fatty degeneration of the cuff muscle and a positive correlation with isokinetic muscle torque.
The high-grade partial-thickness rotator cuff tears showed more severe tendinosis compared with the small full-thickness tears in this study. Contrary to previous impressions that tear size or fatty infiltration is the factor that most influences healing, tendinosis severity assessed by preoperative MRI was the only factor associated with failure to heal, given the numbers available for analysis, in patients with partial-thickness and small full-thickness rotator cuff tears. Surgeons should pay more attention to tendon quality during repair surgery or rehabilitation in smaller rotator cuff tears, especially in high-grade partial-thickness tears with severe tendinosis.
Smoking affected healing failure after arthroscopic rotator cuff repair. Attention should be paid to smokers, especially current heavy smokers, in cases of rotator cuff repair surgery.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.