RESUMO
AIMS: The diagnosis of developmental dysplasia of the hip (DDH) is challenging owing to extensive variation in paediatric pelvic anatomy. Artificial intelligence (AI) may represent an effective diagnostic tool for DDH. Here, we aimed to develop an anteroposterior pelvic radiograph deep learning system for diagnosing DDH in children and analyze the feasibility of its application. METHODS: In total, 10,219 anteroposterior pelvic radiographs were retrospectively collected from April 2014 to December 2018. Clinicians labelled each radiograph using a uniform standard method. Radiographs were grouped according to age and into 'dislocation' (dislocation and subluxation) and 'non-dislocation' (normal cases and those with dysplasia of the acetabulum) groups based on clinical diagnosis. The deep learning system was trained and optimized using 9,081 radiographs; 1,138 test radiographs were then used to compare the diagnoses made by deep learning system and clinicians. The accuracy of the deep learning system was determined using a receiver operating characteristic curve, and the consistency of acetabular index measurements was evaluated using Bland-Altman plots. RESULTS: In all, 1,138 patients (242 males; 896 females; mean age 1.5 years (SD 1.79; 0 to 10) were included in this study. The area under the receiver operating characteristic curve, sensitivity, and specificity of the deep learning system for diagnosing hip dislocation were 0.975, 276/289 (95.5%), and 1,978/1,987 (99.5%), respectively. Compared with clinical diagnoses, the Bland-Altman 95% limits of agreement for acetabular index, as determined by the deep learning system from the radiographs of non-dislocated and dislocated hips, were -3.27° - 2.94° and -7.36° - 5.36°, respectively (p < 0.001). CONCLUSION: The deep learning system was highly consistent, more convenient, and more effective for diagnosing DDH compared with clinician-led diagnoses. Deep learning systems should be considered for analysis of anteroposterior pelvic radiographs when diagnosing DDH. The deep learning system will improve the current artificially complicated screening referral process. Cite this article: Bone Joint J 2020;102-B(11):1574-1581.
Assuntos
Inteligência Artificial , Diagnóstico por Computador , Luxação Congênita de Quadril/diagnóstico por imagem , Pré-Escolar , Feminino , Luxação Congênita de Quadril/diagnóstico , Humanos , Interpretação de Imagem Assistida por Computador , Lactente , Recém-Nascido , MasculinoRESUMO
UNLABELLED: : Stem cell therapy has emerged as a new strategy for treatment of ischemic heart disease. Although umbilical cord-derived mesenchymal stromal cells (UC-MSCs) have been used preferentially in the acute ischemia model, data for the chronic ischemia model are lacking. In this study, we investigated the effect of UC-MSCs originated from Wharton's jelly in the treatment of chronic myocardial ischemia in a porcine model induced by ameroid constrictor. Four weeks after ameroid constrictor placement, the surviving animals were divided randomly into two groups to undergo saline injection (n = 6) or UC-MSC transplantation (n = 6) through the left main coronary artery. Two additional intravenous administrations of UC-MSCs were performed in the following 2 weeks to enhance therapeutic effect. Cardiac function and perfusion were examined just before and at 4 weeks after intracoronary transplantation. The results showed that pigs with UC-MSC transplantation exhibited significantly greater left ventricular ejection fraction compared with control animals (61.3% ± 1.3% vs. 50.3% ± 2.0%, p < .05). The systolic thickening fraction in the infarcted left ventricular wall was also improved (41.2% ± 3.3% vs. 46.2% ± 2.3%, p < .01). Additionally, the administration of UC-MSCs promoted collateral development and myocardial perfusion. The indices of fibrosis and apoptosis were also significantly reduced. Immunofluorescence staining showed clusters of CM-DiI-labeled cells in the border zone, some of which expressed von Willebrand factor. These results suggest that UC-MSC treatment improves left ventricular function, perfusion, and remodeling in a porcine model with chronic myocardial ischemia. SIGNIFICANCE: Ischemic heart disease is the leading cause of death worldwide. Many patients with chronic myocardial ischemia are not suitable for surgery and have no effective drug treatment; they are called "no-option" patients. This study finds that umbilical cord-derived mesenchymal stromal cells transplanted by intracoronary delivery combined with two intravenous administrations was safe and could significantly improve left ventricular function, perfusion, and remodeling in a large-animal model of chronic myocardial ischemia, which provides a new choice for the no-option patients. In addition, this study used clinical-grade mesenchymal stem cells with delivery and assessment methods commonly used clinically to facilitate further clinical transformation.