（1）Functional brain network identification and fMRI augmentation using aVAE-GAN framework
Ning Qiang a,b,1 , Jie Gao a,1 , Qinglin Dong c,1 , Huiji Yue a , Hongtao Liang a , Lili Liu a ,Jingjing Yu a , Jing Hu a , Shu Zhang b , Bao Ge a,b , Yifei Sun a , Zhengliang Liu d , Tianming Liu d ,Jin Li a,* , Hujie Song e,**, Shijie Zhao f,***
Keywords:fMRI Functional brain network Variational auto-encoder Generative adversarial net Data augmentation Brain disorders
ABSTRACT Recently, deep learning models have achieved superior performance for mapping functional brain networks fromfunctional magnetic resonance imaging (fMRI)data compared with traditional methods. However, due to thelack of sufficient data and the high dimensionality of brain volume, deep learning models of fMRI tendtufferfrom overfitting. In addition, existing methods rarely studied fMRI data augmentation and its application. Toaddress these issues, we developed a VAE-GAN framework that combined a VAE (variational auto-encoder) witha GAN (generative adversarial net) for functional brain network identification and fMRI augmentation. As agenerative model, the VAE-GAN models the distribution of fMRI so that it enables the extraction of moregeneralized features, and thus relieve the overfitting issue. The VAE-GAN is easier to train on fMRI than astandard GAN since it uses latent variables from VAE to generate fake data rather than relying on random noisethat is used in a GAN, and it can generate higher quality of fake data than VAE since the discriminator canpromote the training of the generator. In other words, the VAE-GAN inherits the advantages of VAE and GAN andavoids their limitations in modeling of fMRI data. Extensive experiments on task fMRI datasets from HCP haveproved the effectiveness and superiority of the proposed VAE-GAN framework for identifying both temporalfeatures and functional brain networks compared with existing models, and the quality of fake data is higher thanthose from VAE and GAN. The results on resting state fMRI of Attention Deficit Hyperactivity Disorder (ADHD)-200 dataset further demonstrated that the fake data generated by the VAE-GAN can help improve the performance of brain network modeling and ADHD classification
（2）中医儿科临床诊疗指南·孤独症谱系障碍
赵宁侠，宋虎杰，杜晓刚，高峰，樊亚妮，张倩，焦文涛，郭凯，张宁勃（陕西中医药大学附属西安中医脑病医院，西安 710032）
摘要：通过文献检索、文献评价、文献研究总结、3轮专家问卷调查、专家论证会、专家质量方法学评价和临床一致性评价，制定《中医儿科临床诊疗指南·孤独症谱系障碍》。本指南提出了孤独症谱系障碍（ASD）的诊断、辨证、治疗、预防和调护建议，适用于18周岁以下人群孤独症谱系障碍的诊断和防治，适合中医科、儿科、精神科、心理科等相关临床医师使用。
关键词：中医儿科；临床诊疗指南；孤独症谱系障碍；标准化
（3）乔树真治疗郁病用药经验*
段瑞娟1 ，宋虎杰2 ，乔树真3 ，曹朗朗1 ，宋楚君1(1.陕西中医药大学，陕西 咸阳 712046；2.西安中医脑病医院，陕西 西安710032；3.陕西省中医医院，陕西 西安710003)
[摘要] 总结乔树真教授治疗郁病的临床经验。乔树真教授治疗郁病主要从肝、心、脾等脏腑论治，其认为临床常见肝郁脾虚证及肝经郁热证，治以疏肝解郁、健脾清心安神，自拟乔氏解郁安神汤加减治疗，临床疗效明显。附病案2则以资验证。
[关键词] 郁病；抑郁；抑郁合并焦虑；肝郁脾虚；肝经郁热；乔树真；乔氏解郁安神汤；名医经验
3、项目
（1)个体化脑功能区剖分(pBFS)技术指导下精准神经调控干预治疗孤独症谱系障碍研究——多中心随机双盲对照试验
(2)痉挛型脑瘫中西医结合真实世界临床研究
(3)省部共建中医湿证国家重点实验室重点项目 脑血管疾病风险人群湿证相关特征的前瞻性、多中心队列研究
(4)中国中风病中医药注册登记研究(China Stroke Registry for Patients With Traditional Chinese Medicine,CASES-TCM)分中心合作协议书
(5)中西医结合治疗孤独症谱系障碍真实世界临床研究
