目的:探讨基于影像组学的多参数MRI定量指标在膀胱癌肌层浸润分析中的价值。方法:回顾性收集符合纳入标准的膀胱癌患者225例,其中非肌层浸润性膀胱癌125例,肌层浸润性膀胱癌100例。在MR T2WI、DWI及增强图像上测量肿瘤-壁界面,并运用影...目的:探讨基于影像组学的多参数MRI定量指标在膀胱癌肌层浸润分析中的价值。方法:回顾性收集符合纳入标准的膀胱癌患者225例,其中非肌层浸润性膀胱癌125例,肌层浸润性膀胱癌100例。在MR T2WI、DWI及增强图像上测量肿瘤-壁界面,并运用影像组学软件对肿瘤区域进行勾画及特征筛选,然后基于3组特征的概率值构建单参数及多参数联合模型,选择最优概率值与肿瘤-壁界面构建诺模图模型,在外部验证集中测试其诊断性能。ROC曲线及校准曲线对模型准确性进行评估。结果:最终选用基于6个特征的多参数联合概率值,与肿瘤-壁界面联合构建Nomogram模型,在ROC曲线上训练集和测试集曲线下面积(Area under curve,AUC)分别为0.892、0.875,表现出良好的诊断性能,较单独的组学模型或肿瘤-壁界面模型有更好的准确性。外部验证模型的AUC为0.846,进一步证明该模型有较好的预测性能。结论:基于多参数MRI和肿瘤-壁界面构建的Nomogram模型在膀胱癌是否有肌层浸润的鉴别上具有较好的诊断性能及可重复性,可以协助临床医生做出有效评估。展开更多
We developed an H5/H7 trivalent inactivated vaccine by using Re-11, Re-12, and H7-Re2 vaccine seed viruses, which were generated by reverse genetics and derived their HA genes from A/duck/Guizhou/S4184/2017(H5N6) (DK/...We developed an H5/H7 trivalent inactivated vaccine by using Re-11, Re-12, and H7-Re2 vaccine seed viruses, which were generated by reverse genetics and derived their HA genes from A/duck/Guizhou/S4184/2017(H5N6) (DK/GZ/S4184/17) (a clade 2.3.4.4d virus), A/chicken/Liaoning/SD007/2017(H5N1) (CK/LN/SD007/17) (a clade 2.3.2.1d virus), and A/chicken/ Guangxi/SD098/2017(H7N9) (CK/GX/SD098/17), respectively. The protective efficacy of this novel vaccine and that of the recently used H5/H7 bivalent inactivated vaccine against different H5 and H7N9 viruses was evaluated in chickens. We found that the H5/H7 bivalent vaccine provided solid protection against the H7N9 virus CK/GX/SD098/17, but only 50–60% protection against different H5 viruses. In contrast, the novel H5/H7 trivalent vaccine provided complete protection against the H5 and H7 viruses tested. Our study underscores the importance of timely updating of vaccines for avian influenza control.展开更多
文摘目的:探讨基于影像组学的多参数MRI定量指标在膀胱癌肌层浸润分析中的价值。方法:回顾性收集符合纳入标准的膀胱癌患者225例,其中非肌层浸润性膀胱癌125例,肌层浸润性膀胱癌100例。在MR T2WI、DWI及增强图像上测量肿瘤-壁界面,并运用影像组学软件对肿瘤区域进行勾画及特征筛选,然后基于3组特征的概率值构建单参数及多参数联合模型,选择最优概率值与肿瘤-壁界面构建诺模图模型,在外部验证集中测试其诊断性能。ROC曲线及校准曲线对模型准确性进行评估。结果:最终选用基于6个特征的多参数联合概率值,与肿瘤-壁界面联合构建Nomogram模型,在ROC曲线上训练集和测试集曲线下面积(Area under curve,AUC)分别为0.892、0.875,表现出良好的诊断性能,较单独的组学模型或肿瘤-壁界面模型有更好的准确性。外部验证模型的AUC为0.846,进一步证明该模型有较好的预测性能。结论:基于多参数MRI和肿瘤-壁界面构建的Nomogram模型在膀胱癌是否有肌层浸润的鉴别上具有较好的诊断性能及可重复性,可以协助临床医生做出有效评估。
基金This work was supported by the National Key R&D Program of China(2016YFD0501602,2017YFD0500701,and 2016YFEO203200)the National Natural Science Foundation of China(3167131307)+1 种基金the China Agriculture Research System(CARS-41-G12)and Central Publicinterest Scientific Institution Basal Research Fund(1610302017001).
文摘We developed an H5/H7 trivalent inactivated vaccine by using Re-11, Re-12, and H7-Re2 vaccine seed viruses, which were generated by reverse genetics and derived their HA genes from A/duck/Guizhou/S4184/2017(H5N6) (DK/GZ/S4184/17) (a clade 2.3.4.4d virus), A/chicken/Liaoning/SD007/2017(H5N1) (CK/LN/SD007/17) (a clade 2.3.2.1d virus), and A/chicken/ Guangxi/SD098/2017(H7N9) (CK/GX/SD098/17), respectively. The protective efficacy of this novel vaccine and that of the recently used H5/H7 bivalent inactivated vaccine against different H5 and H7N9 viruses was evaluated in chickens. We found that the H5/H7 bivalent vaccine provided solid protection against the H7N9 virus CK/GX/SD098/17, but only 50–60% protection against different H5 viruses. In contrast, the novel H5/H7 trivalent vaccine provided complete protection against the H5 and H7 viruses tested. Our study underscores the importance of timely updating of vaccines for avian influenza control.