The classification of thymoma has always been controversial topil in recent years. It hasn’t been unified because of the morphological diversity of thymoma, the heterogeneity of tumour cells and the lack of simple and effective observation index. With the development of diagnostic technique and oncobiology research, several classification methods have been drawn off, including its World Health Organization(WHO) lassification. We reviewed the main classification and discussed the problems of each classification method and their clinical guiding significamce, summarized the development tendency, methods assist the classification and clinical research of thymoma.
Microaneurysm is the initial symptom of diabetic retinopathy. Eliminating this lesion can effectively prevent diabetic retinopathy in the early stage. However, due to the complex retinal structure and the different brightness and contrast of fundus image because of different factors such as patients, environment and acquisition equipment, the existing detection algorithms are difficult to achieve the accurate detection and location of the lesion. Therefore, an improved detection algorithm of you only look once (YOLO) v4 with Squeeze-and-Excitation networks (SENet) embedded was proposed. Firstly, an improved and fast fuzzy c-means clustering algorithm was used to optimize the anchor parameters of the target samples to improve the matching degree between the anchors and the feature graphs; Then, the SENet attention module was embedded in the backbone network to enhance the key information of the image and suppress the background information of the image, so as to improve the confidence of microaneurysms; In addition, an spatial pyramid pooling was added to the network neck to enhance the acceptance domain of the output characteristics of the backbone network, so as to help separate important context information; Finally, the model was verified on the Kaggle diabetic retinopathy dataset and compared with other methods. The experimental results showed that compared with other YOLOv4 network models with various structures, the improved YOLOv4 network model could significantly improve the automatic detection results such as F-score which increased by 12.68%; Compared with other network models and methods, the automatic detection accuracy of the improved YOLOv4 network model with SENet embedded was obviously better, and accurate positioning could be realized. Therefore, the proposed YOLOv4 algorithm with SENet embedded has better performance, and can accurately and effectively detect and locate microaneurysms in fundus images.
Abstract： Objective To explore the impact of obesity on postoperative morbidity and mortality after pneumonectomy. Methods Clinical data of 3 494 patients with pulmonary diseases who underwent pneumonectomy in Shanghai Pulmonary Hospital from September 2003 to December 2007 were retrospectively analyzed. All the 3 494 patients were divided into two groups according to the patients’ preoperative body mass index （BMI）. There were 3 340 patients in the non-obesity group （BMI＜28 kg/m2） including 2 502 males and 838 females with their average age of 61.9±10.7 years， and 154 patients in the obesity group （BMI≥28 kg/m2） including 87 males and 67 females with their average age of 59.7±9.6 years. Univariate analysis and logistic regression were used to analyze the impact of obesity （BMI≥28 kg/m2） on postoperative morbidity after pneumonectomy. Results There were a total of 26 cases of perioperative death， including 23 patients in the non-obesity group and 3 patients in the obesity group. There was no statistical difference in mortality between the two groups ［0.7% （23/3 340） vs. 1.9% （3/154）， P=0.118］. There was no statistical difference in any particular postoperative morbidity or incidence of pulmonary complications between the two groups （P＞0.05）. Other than pulmonary complications， the incidence of postoperative complication in other body systems of the obesity group was significant higher than that of the non-obesity group （P＜0.05）. The incidence of cerebrovascular accidents， myocardial infarction and acute renal failure of the obesity group was significant higher than those of the non-obesity group （P＜0.05）. Logistic regression showed that obesity （BMI≥28 kg/m2） was not an independent risk factor for postoperative morbidity after pneumonectomy ［B=0.648， OR=1.911， 95% CI（0.711， 5.138），P=0.199］. Conclusion Obesity is not a significant risk factor of postoperative mortality or morbidity after pneumonectomy.