OBJECTIVE To study the constituents from the dried stems and leaves of Illicium dunnianum Tutcher.METHODS The compounds were isolated and purified by column chromatography of AB-8 macroporous resin,silica gel,HW-40C,ODS,Sephadex LH-20,and semi-preparative RP-HPLC.Their structures were elucidated by physicochemical properties,spectral analyses and ECD.RESULTS The 70%ethanol extract of Illicium dunnianum was subjected to AB-8 macroporous adsorption resin CC to yield 30%ethanol fraction.Five compounds were obtained and characterized as anisole glycol-7-O-β-L-funanarabifuranosyl-(1→6)-β-D-glucopyranoside(1),4-O-β-D-glucopyranosyloxy-benzaldehyde(2),benzyl-O-α-L-rhamnopyranosyl-(1→6)-β-D-glucopyranoside(3),β-D-glucopyranoside benzoate(4)and sachalinoside B(5),respectively.CONCLUSION Compound 1 is a new phenolic glycoside,2-5 are identified from Illicium dunnianum for the first time.

OBJECTIVE To study the constituents from the dried stems and leaves of Illicium dunnianum Tutcher.METHODS The compounds were isolated and purified by column chromatography of AB-8 macroporous resin,silica gel,HW-40C,ODS,Sephadex LH-20,and semi-preparative RP-HPLC.Their structures were elucidated by physicochemical properties,spectral analyses and ECD.RESULTS The 70%ethanol extract of Illicium dunnianum was subjected to AB-8 macroporous adsorption resin CC to yield 30%ethanol fraction.Five compounds were obtained and characterized as anisole glycol-7-O-β-L-funanarabifuranosyl-(1→6)-β-D-glucopyranoside(1),4-O-β-D-glucopyranosyloxy-benzaldehyde(2),benzyl-O-α-L-rhamnopyranosyl-(1→6)-β-D-glucopyranoside(3),β-D-glucopyranoside benzoate(4)and sachalinoside B(5),respectively.CONCLUSION Compound 1 is a new phenolic glycoside,2-5 are identified from Illicium dunnianum for the first time.

To construct a recombinant fowl adenovirus 4(FAdV-4)expressing the Cap protein of goose astrovirus genotype 2(GoAstV-2),the expression cassette of Cap gene was inserted into the natural 1 966 bp deletion region of the FAdV-4 genome in the infectious clone p15A-cm-FAdV4-HNJZ.The resulted recombinant plasmid p15A-cm-FAdV4-HNJZ-Cap/GoAstV-2 was linearized with restriction enzyme and transfected into chicken hepatoma cell line(LMH)to rescue the recombinant FAdV-4 expressing the Cap protein of GoAstV-2,rF Ad V4-Cap/GoAstV-2.After 15 passages in LMH cells,the recombinant rFAdV4-Cap/GoAstV-2 was identified by PCR using primers flanking the insertion site of the Cap gene expression cassette and using viral genome DNA extracted from rFAdV4-Cap/GoAstV-2 infected LMH cells as template.LMH cells were in-fected with 15th passage rFAdV4-Cap/GoAstV-2 and indirect immunofluorescence was performed with a polyclonal antibody against Cap protein as the primary antibody.Western blot was carried out with lysates of rFAdV4-Cap/GoAstV-2 infected LMH cells.The in vitro replication dynamic of the 15th passage of the rFAdV4-Cap/GoAstV-2 was also investigated in LMH cells.The results demonstrated that the Cap gene of GoAstV-2 was presented in the genome of the recombinant vi-rus rF AdV4-Cap/Go Ast V-2,and could be expressed stably.The prepared recombinant virus in this study will lay a foundation for developing inactivated bivalent vaccine candidate against co-in-fection of FAdV-4 and GoAstV-2 in goose.

To construct a recombinant fowl adenovirus 4(FAdV-4)expressing the Cap protein of goose astrovirus genotype 2(GoAstV-2),the expression cassette of Cap gene was inserted into the natural 1 966 bp deletion region of the FAdV-4 genome in the infectious clone p15A-cm-FAdV4-HNJZ.The resulted recombinant plasmid p15A-cm-FAdV4-HNJZ-Cap/GoAstV-2 was linearized with restriction enzyme and transfected into chicken hepatoma cell line(LMH)to rescue the recombinant FAdV-4 expressing the Cap protein of GoAstV-2,rF Ad V4-Cap/GoAstV-2.After 15 passages in LMH cells,the recombinant rFAdV4-Cap/GoAstV-2 was identified by PCR using primers flanking the insertion site of the Cap gene expression cassette and using viral genome DNA extracted from rFAdV4-Cap/GoAstV-2 infected LMH cells as template.LMH cells were in-fected with 15th passage rFAdV4-Cap/GoAstV-2 and indirect immunofluorescence was performed with a polyclonal antibody against Cap protein as the primary antibody.Western blot was carried out with lysates of rFAdV4-Cap/GoAstV-2 infected LMH cells.The in vitro replication dynamic of the 15th passage of the rFAdV4-Cap/GoAstV-2 was also investigated in LMH cells.The results demonstrated that the Cap gene of GoAstV-2 was presented in the genome of the recombinant vi-rus rF AdV4-Cap/Go Ast V-2,and could be expressed stably.The prepared recombinant virus in this study will lay a foundation for developing inactivated bivalent vaccine candidate against co-in-fection of FAdV-4 and GoAstV-2 in goose.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.