1.Comparative study of two different methods for automatic segmentation of organs at risk in head and neck region
Shuming ZHANG ; Ruijie YANG ; Senhua ZHU ; Hao WANG ; Suqing TIAN ; Xuyang ZHANG ; Jiaqi LI ; Runhong LEI
Chinese Journal of Radiological Medicine and Protection 2020;40(5):385-391
Objective:To develope a deep-learning-based auto-segmentation model to segment organs at risk (OARs) in head and neck (H&N) region and compare with atlas-based auto-segmentation software (Smart segmentation).Methods:The auto-segmentation model consisted of classification model and segmentation model based on deep learning neural network. The classification model was utilized to classify CT slices into six categories in the cranio-caudal direction, and then the CT slices corresponding to the categories for different OARs were pushed to the segmentation model respectively. The CT image data of 150 patients were used for auto-segmentation model training and building atlas library in Smart segmentation software. Another 20 patients were used as testing dataset for both auto-segmentation model and Smart segmentation software. Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to evaluate the accuracy of two method, and auto-segmentation time cost was recorded. Paired Student′s t-test or non-parametric Wilcoxon signed-rank test was performed depending on result of normality test. Results:The DSC and HD of auto-segmentation model for brainstem, left eye, right eye, left optic nerve, right optic nerve, left temporal lobe, right temporal lobe, mandible, left parotid and right parotid were 0.88 and 4.41 mm, 0.89 and 2.00 mm, 0.89 and 2.12 mm, 0.70 and 3.00 mm, 0.80 and 2.24 mm, 0.81 and 7.98 mm, 0.84 and 8.82 mm, 0.89 and 5.57 mm, 0.70 and 11.92 mm, 0.77 and 11.27 mm respectively. The results of auto-segmentation model were better than those of Smart segmentation ( t=3.115-7.915, Z=-1.352 to -3.921, P<0.05) except left and right parotids. In addition, the speed of auto-segmentation model was 51.28% faster than that of Smart segmentation. Conclusions:In this study, the deep-learning-based auto-segmentation model demonstrated superior performance in accuracy and efficiency on segmenting OARs in H&N CT images, which was better than Smart segmentation software.
2.Study on the Effect and Mechanism of Total Flavonoids from Marchantia convoluta on the Anti-hepatic Fibrosis in Mice
Shuang LIANG ; Hua ZHU ; Jianjun HUANG ; Wentao ZHANG ; Senhua LU ; Shiman CHEN
China Pharmacy 2021;32(19):2363-2370
OBJECTIVE:To study the effect and potential mechanism of the total flavonoids from Marchantia convoluta on anti-hepatic fibrosis in the mice. METHODS :Seventy-two mice were randomly divided into blank group ,model group ,positive control group (colchicine 0.2 mg/kg)and M. convoluta total flavonoids high-dose ,medium-dose and low-dose groups (300,150, 75 mg/kg),with 12 mice in eac group. Except for blank group ,other groups were subcutaneously given 25% CCl4-peanut oil solution on the back to induce liver fibrosis model. At the same time ,blank group and model group were given water intragastrically,while other groups were given relevant medicine intragastrically 20 mL/kg,once a day ,for consecutive 10 weeks. After last administration ,the serum levels of ALT and AST were detected . Histopathological changes of liver tissue in mice was observed. The levels of COL- Ⅰ,COL-Ⅲ and TGF-β1 in liver tissue were detected . The protein expression levels of α-SMA and TGF-β1,Smad2,Smad4 and Smad 7 in liver tissue were detected . The expression levels of TGF-β1,Smad2,Smad4 and Smad 7 mRNA in liver tissue were detected . RESULTS :Compared with blank group ,the serum levels of ALT and AST in model group,the levels of COL- Ⅰ,COL-Ⅲ and TGF-β1 in liver tissue,protein expression levels of α-SMA,TGF-β1,Smad2 and Smad 4,mRNA expression levels of TGF-β1,Smad2 and Smad4 were increased significantly (P<0.05 or P<0.01).The mRNA and protein expression levels of Smad 7 in liver tis sue were decreased significantly (P<0.05). The degree of liver tissue injury and collagen fiber hyperplasia were serious. Compared with model group ,above indexes of mice were reversed significantly in positive control group and M. convoluta total flavonoids high-dose group (P<0.05 or P<0.01). Serum level of ALT ,the levels of COL- Ⅰ,mRNA and protein expression of TGF-β1,Smad2 and Smad 4 in liver tissue were decreased significantly in M. convoluta total flavonoids medium-dose group (P<0.05 or P<0.01). Protein expression of Smad 2 and Smad 4 in liver tissue were decreased significantly in M. convoluta total flavonoids low-dose group (P<0.05). The liver injury and fibrosis of mice were relieved in administration groups. CONCLUSIONS :M. convoluta total flavonoids possess the effect of anti-hepatic fibrosis ,the mechanism of which is related to the regulation of mRNA and protein expression of TGF-β1,Smad2,Smad4 and Smad 7 in the signaling pathway of TGF-β/Smad.