Advanced Faster RCNN: a non-contrast CT-based algorithm for detecting pancreatic lesions in multiple disease stages / 南方医科大学学报

OBJECTIVE@#To propose a non-contrast CT-based algorithm for automated and accurate detection of pancreatic lesions at a low cost.@*METHODS@#With Faster RCNN as the benchmark model, an advanced Faster RCNN (aFaster RCNN) model for pancreatic lesions detection based on plain CT was constructed. The model uses the residual connection network Resnet50 as the feature extraction module to extract the deep image features of pancreatic lesions. According to the morphology of pancreatic lesions, 9 anchor frame sizes were redesigned to construct the RPN module. A new Bounding Box regression loss function was proposed to constrain the training process of RPN module regression subnetwork by comprehensively considering the constraints of the lesion shape and anatomical structure. Finally, a detection frame was generated using the detector in the second stage. The data from a total of 728 cases of pancreatic diseases from 4 clinical centers in China were used for training (518 cases, 71.15%) and testing (210 cases, 28.85%) of the model. The performance of aFaster RCNN was verified through ablation experiments and comparison experiments with 3 classical target detection models SSD, YOLO and CenterNet.@*RESULTS@#The aFaster RCNN model for pancreatic lesion detection achieved recall rates of 73.64% at the image level and 92.38% at the patient level, with an average precision of 45.29% and 53.80% at the image and patient levels, respectively, which were higher than those of the 3 models for comparison.@*CONCLUSION@#The proposed method can effectively extract the imaging features of pancreatic lesions from non-contrast CT images to detect the pancreatic lesions.

Establishment of a TreeNet algorithm-based model for early prediction of essential hypertension / 预防医学

Objective@#To create a model for early prediction of essential hypertension (EH) based on the TreeNet algorithm, so as to provide a tool for early monitoring of EH. @*Methods@#The health examination data were collected from individuals receiving health examinations in Hangzhou Haiqin Health Examination Center or Shanghai Yibao Health Management Co., Ltd from 2014 to 2016, and a predictive model for EH was created based on the TreeNet algorithm. The effectiveness of the model for early prediction of EH was evaluated using root mean square error (RMSE), mean absolute deviation (MAD), coefficient of determination (R2) and receiver operating characteristic (ROC) curve. @*Results@#A total of 12 variables were included in the model, and the highest contributing variable was body mass index (BMI), followed by BMI difference, two-year BMI difference, two-year triglyceride (TG) difference, two-year total cholesterol (TC) difference, high-density lipoprotein cholesterol (HDL-C) in 2014, TG in 2014, low-density lipoprotein cholesterol (LDL-C) in 2014, body weight in 2015, fasting blood glucose in 2015, TG in 2015, urea nitrogen difference and platelet in 2015. The highest predictive accuracy was 100.00%, and the lowest was 56.89%. The risk of EH significantly increased among individuals with BMI in 2015 of >25 kg/m2, two-year BMI difference of >0.5 kg/m2, two-year TG difference ranging from 1.3 to 3.3 mmol/L, TC in 2015 of 2.0 to 2.4 mmol/L and HDL-C in 2014 of <0.52 mmol/L. The model presented RMSE of 0.082, MAD of 0.064, R2 of 0.811, area under the ROC curve of 0.788 (95%CI: 0.741-0.815), sensitivity of 69.05% and specificity of 66.21% for prediction of EH@*Conclusion@# The TreeNet algorithm-based model is effective for early monitoring of high-risk individuals for EH.

Fast track surgery in laparoscopic liver resection / 中华普通外科杂志

Objective To evaluate the value of fast track surgery (FTS) in laparoscopic hepatectomy.Methods The clinical data of 142 patients undergoing laparoscopic liver resection from January 2014 to January 2016 were analyzed retrospectively.74 patients received fast track surgery treatment (FTS group) and 68 patients received traditional treatment methods (control group).Results Compared with control group,FTS group had a shorter operative time and less blood lose (t =2.279,t =2.432,P ＜0.05),quicker postoperative intestinal function recovery (t =3.548,P ＜ 0.05),a shorter postoperative hospitalization time (t =2.821,P ＜ 0.05),a lower hospitalization cost (t =2.507,P ＜ 0.05),a lower postoperative VAS scores (t =3.394,t =3.176,t =7.079,P ＜ 0.05) in 3 post-op successive days.There were 3 patients with major post-op complications in FTS group (4.05％,3/74) compared with 4 cases in control group (5.88％,4/68) (x2 =0.253,P ＞ 0.05).Conclusion The application of fast track surgery in laparoscopic liver resection is safe and effective,and helpful in reducing patients' inhospital cost.

A modified approach to establishing a rat model of liver cancer with concurrent cirrhosis / 南方医科大学学报

<p><b>OBJECTIVE</b>To establish a modified rat model of liver cancer with concurrent cirrhosis for the study of carcinogenesis characteristics and drug intervention of liver cancer.</p><p><b>METHODS</b>Fifty male Wistar rats weighing 100-120 g were randomly divided into normal control group (20 rats) and model group (30 rats). In the model group, the rats were subjected to intraperitoneal injection of 50 mg/kg DEN N-diethylnitrosamine (DEN) twice a week for 4 consecutive weeks, followed then by weekly injections for another 10 weeks. The control rats received injections of 0.1 ml saline in the same manner. At 2, 4, 8, 12, 14, and 18 weeks, 3 rats from each group were sacrificed for assessing tumor formation and liver cirrhosis.</p><p><b>RESULTS</b>Liver cancer with concurrent cirrhosis was induced successfully after 14 weeks of DEN injections. At the 14th week, 3 out of the 5 rats were found to have cirrhosis and LC, and at the 18th week, all the 3 rats examined had cirrhosis and liver cancer. The total carcinogenesis rate in the rats was 75% at 18 weeks with an overall mortality of 33%.</p><p><b>CONCLUSION</b>This approach to establishing rat models of liver cancer with concurrent cirrhosis requires simple operation, shortens the time of carcinogenesis, and ensures a high success rate of carcinogenesis and a low mortality rate. The carcinogenesis characteristics in this model are similar to those in human.</p>

Protective effect of alkaline phosphatase on acute lung injury after orthotopic autologous liver transplantation in rats / 中国组织工程研究

AIM:The complications following liver transplantation consist of the liver damage and the function failure of other organs,among which lung is the most prone and the earliest affected lesion.By establishing an autologous orthotopic liver transplantation(OLT) model in rats,this study was to investigate the acute lung injury after liver transplantation and the role of alkaline phosphatase(AP) in protection of the injury.METHODS:①The experiments were performed in the Test Animal Center and Digestion Laboratory,Nanfang Hospital,Southern Medical University from May to October in 2007.All the proposals were in accordance with the ethical standard of animals.② Twenty-four SD rats were randomly divided into three groups:sham-operation control group,autologous OLT group and AP group,each containing 8 animals.Autologous OLT models were induced in OLT group and AP group,while control group,the abdomen was only opened and then closed besides the liver lobes were isolated.Lingual vein injection of AP was given in AP group 5 minutes before the blood supply of the liver restored.③The concentration of myeloperoxidase(MPO),malondialdehyde(MDA) and surfactant protein A(SP-A) in lung tissue were respectively examined in each group,lung dry-to-wet weight ratio was also measured.Furthermore,hepatic and lung pathological sections were observed.RESULTS:All the 24 rats were involved in the result analysis.①Compared to control group,the concentration of MPO and MDA in lung tissue were significantly increased in OLT group and AP group(P