Objective To systematic evaluate the efficacy and safety of the endovascular aortic repair （endovascular stent placement） and open operation in treatment of acute Stanford type B aortic dissection. Methods The literatures about clinical controlled trials of endovascular aortic repair and open operation in treatment of acute Stanford type B aortic dissection that were included in CNKI， Wanfang data， VIP， Cochrane Central Register of Controlled Trials of the Cochrane Library， OVID， Pubmed Medline， EBSCO， EMBASE， Springer Link，Science Direct， and other databases from January 1991 to January 2013 were retrieved by computer. RevMan 5.1 software were used to analyze the clinical trial data. Results Eight trials （5 618 patients with acute Stanford type B aortic dissection） were included in the analysis.There was statistically significant difference of the 30 d mortality after operation between the endovascular repair group and the open operation group， which endovascular repair group was significantly better than the open operation group〔OR=0.55，95% CI （0.46-0.65）， P＜0.000 01〕. In addition， there were significant difference between the incidence of stroke 〔OR=0.57， 95% CI （0.39-0.84）， P=0.005〕， respiratory failure 〔OR=0.64， 95% CI （0.53-0.78）， P＜0.000 01〕， and cardiac complications 〔OR=0.49，95% CI （0.38-0.64），P＜0.000 01〕，which endovascular repair group was better than the open operation group. However，endovascular repair could not improve the postoperative outcomes of paraplegia〔OR=1.30，95% CI （0.82-2.05），P=0.26〕 and acute renal failure 〔OR=0.86，95% CI （0.41-1.80），P=0.69〕. Conclusion Endovascular repair for treatment acute Stanford type B aortic dissection is preferred method.
Objective To develop a deep learning system for CT images to assist in the diagnosis of thoracolumbar fractures and analyze the feasibility of its clinical application. Methods Collected from West China Hospital of Sichuan University from January 2019 to March 2020, a total of 1256 CT images of thoracolumbar fractures were annotated with a unified standard through the Imaging LabelImg system. All CT images were classified according to the AO Spine thoracolumbar spine injury classification. The deep learning system in diagnosing ABC fracture types was optimized using 1039 CT images for training and validation, of which 1004 were used as the training set and 35 as the validation set; the rest 217 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. The deep learning system in subtyping A was optimized using 581 CT images for training and validation, of which 556 were used as the training set and 25 as the validation set; the rest 104 CT images were used as the test set to compare the deep learning system with the clinician’s diagnosis. Results The accuracy and Kappa coefficient of the deep learning system in diagnosing ABC fracture types were 89.4% and 0.849 (P<0.001), respectively. The accuracy and Kappa coefficient of subtyping A were 87.5% and 0.817 (P<0.001), respectively. Conclusions The classification accuracy of the deep learning system for thoracolumbar fractures is high. This approach can be used to assist in the intelligent diagnosis of CT images of thoracolumbar fractures and improve the current manual and complex diagnostic process.