A Stacked Generalization of 3D Orthogonal Deep Learning Convolutional Neural Networks for Improved Detection of White Matter Hyperintensities in 3D FLAIR Images

BACKGROUND AND PURPOSE:Accurate and reliable detection of white matter hyperintensities and their volume quantification can provide valuable clinical information to assess neurologic disease progression. In this work, a stacked generalization ensemble of orthogonal 3D convolutional neural networks, StackGen-Net, is explored for improving automated detection of white matter hyperintensities in 3D T2-FLAIR images.MATERIALS AND METHODS:Individual convolutional neural networks in StackGen-Net were trained on 2.5D patches from orthogonal reformatting of 3D-FLAIR (n = 21) to yield white matter hyperintensity posteriors. A meta convolutional neural network was trained to learn the functional mapping from orthogonal white matter hyperintensity posteriors to the final white matter hyperintensity prediction. The impact of training data and architecture choices on white matter hyperintensity segmentation performance was systematically evaluated on a test cohort (n = 9). The segmentation performance of StackGen-Net was compared with state-of-the-art convolutional neural network techniques on an independent test cohort from the Alzheimer’s Disease Neuroimaging Initiative-3 (n = 20).RESULTS:StackGen-Net outperformed individual convolutional neural networks in the ensemble and their combination using averaging or majority voting. In a comparison with state-of-the-art white matter hyperintensity segmentation techniques, StackGen-Net achieved a significantly higher Dice score (0.76 [SD, 0.08], F1-lesion (0.74 [SD, 0.13]), and area under precision-recall curve (0.84 [SD, 0.09]), and the lowest absolute volume difference (13.3% [SD, 9.1%]). StackGen-Net performance in Dice scores (median = 0.74) did not significantly differ (P = .22) from interobserver (median = 0.73) variability between 2 experienced neuroradiologists. We found no significant difference (P = .15) in white matter hyperintensity lesion volumes from StackGen-Net predictions and ground truth annotations.CONCLUSIONS:A stacked generalization of convolutional neural networks, utilizing multiplanar lesion information using 2.5D spatial context, greatly improved the segmentation performance of StackGen-Net compared with traditional ensemble techniques and some state-of-the-art deep learning models for 3D-FLAIR.

White matter hyperintensities (WMHs) correspond to pathologic features of axonal degeneration, demyelination, and gliosis observed within cerebral white matter.¹ Clinically, the extent of WMHs in the brain has been associated with cognitive impairment, Alzheimer’s disease and vascular dementia, and increased risk of stroke.^2,3 The detection and quantification of WMH volumes to monitor lesion burden evolution and its correlation with clinical outcomes have been of interest in clinical research.^4,5 Although the extent of WMHs can be visually scored,⁶ the categoric nature of such scoring systems makes quantitative evaluation of disease progression difficult. Manually segmenting WMHs is tedious, prone to inter- and intraobserver variability, and is, in most cases, impractical. Thus, there is an increased interest in developing fast, accurate, and reliable computer-aided automated techniques for WMH segmentation.Convolutional neural network (CNN)-based approaches have been successful in several semantic segmentation tasks in medical imaging.⁷ Recent works have proposed using deep learning–based methods for segmenting WMHs using 2D-FLAIR images.^8-11 More recently, a WMH segmentation challenge¹² was also organized (http://wmh.isi.uu.nl/) to facilitate comparison of automated segmentation of WMHs of presumed vascular origin in 2D multislice T2-FLAIR images. Architectures that used an ensemble of separately trained CNNs showed promising results in this challenge, with 3 of the top 5 winners using ensemble-based techniques.¹²Conventional 2D-FLAIR images are typically acquired with thick slices (3–4 mm) and possible slice gaps. Partial volume effects from a thick slice are likely to affect the detection of smaller lesions, both in-plane and out-of-plane. 3D-FLAIR images, with isotropic resolution, have been shown to achieve higher resolution and contrast-to-noise ratio¹³ and have shown promising results in MS lesion detection using 3D CNNs.¹⁴ Additionally, the isotropic resolution enables viewing and evaluation of the images in multiple planes. This multiplanar reformatting of 3D-FLAIR without the use of interpolating kernels is only possible due to the isotropic nature of the acquisition. Network architectures that use information from the 3 orthogonal views have been explored in recent works for CNN-based segmentation of 3D MR imaging data.¹⁵ The use of data from multiple planes allows more spatial context during training without the computational burden associated with full 3D training.¹⁶ The use of 3 orthogonal views simultaneously mirrors how humans approach this segmentation task.Ensembles of CNNs have been shown to average away the variances in the solution and the choice of model- and configuration-specific behaviors of CNNs.¹⁷ Traditionally, the solutions from these separately trained CNNs are combined by averaging or using a majority consensus. In this work, we propose the use of a stacked generalization framework (StackGen-Net) for combining multiplanar lesion information from 3D CNN ensembles to improve the detection of WMH lesions in 3D-FLAIR. A stacked generalization¹⁸ framework learns to combine solutions from individual CNNs in the ensemble. We systematically evaluated the performance of this framework and compared it with traditional ensemble techniques, such as averaging or majority voting, and state-of-the-art deep learning techniques.     

科研评价导向的改变对中文科技期刊的机遇与挑战

【目的】 值此《中国科技期刊研究》创刊30周年之际,思考科研评价体系的改变给中文科技期刊带来的影响,为中文期刊探寻发展路径。【方法】 结合对中文科技期刊困境的研究,提出应对策略。【结果】 近期国家陆续出台的纠偏评价导向的政策文件,为中文科技期刊既带来了发展机遇,也提出了挑战。【结论】 在重构符合中文科技期刊发展特点的评价体系的基础上,中文科技期刊应明确目标定位,面向国家需求,提升知识服务能力,建立品牌特色。     

氨溴特罗片辅助治疗小儿支原体肺炎的疗效及对机体免疫功能、炎症因子的影响

目的 观察氨溴特罗片辅助治疗小儿支原体肺炎的疗效,探讨其对机体免疫功能、炎症因子的影响.方法 纳入2018年2月至2019年3月西北大学附属神木医院收治的支原体肺炎患儿158例,按照随机数字表法随机分为对照组和观察组,各79例.对照组给予阿奇霉素及对症支持治疗,观察组在对照组基础上加用氨溴特罗片治疗.观察两组总有效率,分析、比较两组治疗前后免疫功能(CD3+、CD4+、CD8+水平)、炎症因子[白细胞介素(IL)-17、单核细胞趋化蛋白-4(MCP-4)、巨噬细胞衍生趋化因子(MDC)]水平,以及核因子-κB(NF-κB)、可溶性髓系细胞触发受体1(sTREM-1)水平变化情况,对比两组不良反应发生情况.结果 观察组总有效率为96.20％,显著高于对照组的86.07％(P<0.05).治疗后两组患儿NF-κB、sTREM-1水平均低于治疗前(P<0.05),治疗后观察组患儿NF-κB、sTREM-1水平低于对照组(P<0.05).治疗后两组IL-17、MCP-4、MDC水平均低于治疗前(P<0.05),治疗后观察组患儿IL-17、MCP-4、MDC水平低于对照组(P<0.05).治疗后两组患儿CD3+、CD4+水平均高于治疗前(P<0.05),CD8+水平均低于治疗前(P<0.05),治疗后观察组患儿CD3+、CD4+水平高于对照组(P<0.05),CD8+水平低于对照组(P<0.05).两组均未发生明显药物相关不良反应.结论 氨溴特罗片辅助治疗小儿支原体肺炎疗效确切,可降低患儿NF-κB、sTREM-1水平,能通过减轻炎性反应、提高免疫功能而发挥作用,安全性良好.     

母亲龋易感性与婴儿口腔微生物多样性关系的纵向探究

目的通过检查有龋及无龋母亲的口腔卫生状况,并通过随访收集其婴儿1个月(1月龄)及6个月(6月龄)的唾液样本测序分析,观察母亲患龋情况对其婴儿口腔微生物多样性的影响。方法通过筛查收集1月龄婴儿的唾液样本;于首次采样时记录母亲的口腔卫生状况,根据母亲患龋情况将婴儿分为母亲有龋组(简称有龋组)和母亲无龋组(简称无龋组),跟踪随访至婴儿6个月时再次收集唾液样本。通过高通量测序的方法,分析婴儿不同月龄微生物多样性的变化。结果本研究随访受试者10例(男6例,女4例),其中有龋组7例,无龋组3例,各组间的微生物群落多样性Shannon指数均无显著性差异(P>0.05)。无龋组婴儿1月龄至6月龄时微生物群落的物种组成有较大变化;有龋组婴儿在1月龄和6月龄时组内各样本间物种组成均差异较大;1月龄时两组微生物群落较相似,而至6月龄时两组婴儿唾液的物种组成已开始发生变化。结论有龋组婴儿口腔内菌群多样性总体高于无龋组,在1月龄至6月龄间婴儿口腔内微生物物种的多样性及丰度均有了不同程度的提高。     

不同波形低频率电刺激对小鼠海马电点燃癫痫的作用比较

目的观察比较不同脉冲波形的低频率电刺激对海马电点燃癫痫模型小鼠的作用差异。方法采用电点燃刺激法建立小鼠癫痫模型, 观察正弦波、单相方波、双相方波低频率电刺激对模型小鼠癫痫行为发作及后放电持续时间的影响, 并比较不同时间点给予正弦波低频率电刺激的抗癫痫作用。结果与对照组比较, 正弦波低频率电刺激30 s能降低小鼠海马电点燃癫痫发作等级(2.85 ± 0.27 vs 4.75 ±0.12, P < 0.05)、减少大发作概率(53.6% vs 96.5%, P < 0.01) 和缩短后放电持续时间[(16.22 ± 1.69) s vs (30.29 ± 1.12) s, P < 0.01], 而单相方波和双相方波低频率电刺激30 s没有明显的抗癫痫作用。常用的单相方波低频率电刺激15 min能降低小鼠海马电点燃发作等级(3.58 ± 0.16, P < 0.05)、减少大发作概率(66.7%, P < 0.01);但对海马后放电持续时间及大发作持续时间无影响(均 P>0.05)。此外, 电点燃刺激前预先给予或结束后3 s内给予正弦波低频率电刺激具有明显的抗癫痫作用( P < 0.05或 P < 0.01), 而电点燃刺激结束10 s给予正弦波低频率电刺激则无上述抗癫痫作用。 结论低频率电刺激抗癫痫作用受波形参数的影响, 其中正弦波低频率电刺激能有效抑制小鼠海马电点燃癫痫的发作。     

中国儿童心脏移植操作规范(2019版)

儿童心脏移植是治疗年龄18岁终末期心力衰竭患者的有效手段。1967年美国Adrian Katrowitz实施第一例儿童心脏移植,近五年全球80家单位每年开展500例左右。中国儿童心脏移植起步晚、发展慢。自1995年开展第一例儿童心脏移植以来,目前国内已登记病例超过130例。中华医学会器官移植学分会组织心脏移植专家,总结国内外相关研究最新进展,结合国际指南和临床实践,针对儿童心脏移植受者选择及常用术式的操作要点、程序和方法,以及各类复杂先天性心脏病心脏移植的特殊操作,制订《中国儿童心脏移植适操作规范(2019版)》。     

新型冠状病毒肺炎出院患者生活质量及影响因素研究

目的:了解新型冠状病毒肺炎(COVID-19)患者出院后的生活质量及其影响因素,为优化早期干预方案,预防社区生活受限,制定相应社区康复措施提供依据。方法:选择2020年3—4月在武汉华润武钢总医院治愈出院的COVID-19患者57例,于2020年4—5月通过"问卷星"平台采用简明健康状况调查量表(SF-12V2)调查患者的生活质量;采用焦虑自评量表(SAS)调查患者的焦虑状态;采用抑郁自评量表(SDS)调查患者的抑郁状态;采用呼吸困难指数量表(mMRC)调查患者的呼吸困难程度。比较不同特征COVID-19患者生活质量的差异;分析患者生活质量与焦虑、抑郁和呼吸困难程度的相关性及其相关的影响因素。结果:共发放57份调查问卷,剔除重复及无效问卷3份,获得有效问卷54份,问卷有效率达94.74%。(1)COVID-19出院后患者生活质量情况:生理总评分和心理总评分分别为(37.02±12.32)分、(38.46±14.42)分;呼吸困难等级0~3级的分别为3例(5.56%)、45例(83.33%)、5例(9.26%)、1例(1.85%);有19例(35.19%)存在焦虑情绪(SAS≥50分)和抑郁情绪(SDS≥53分)。(2)不同特征COVID-19患者生活质量比较:不同疾病分型的患者在生理总评分方面差异有统计学意义(P<0.05)。(3)生活质量与焦虑、抑郁和呼吸困难程度的相关性分析:Pearson相关分析结果显示,SF-12V2生理总评分与焦虑程度(r=-0.34,P=0.011)和呼吸困难程度(r=-0.39,P=0.003)之间存在负相关性,SF-12V2心理总评分与焦虑程度(r=-0.46,P=0.001)和抑郁程度(r=-0.40,P=0.002)之间存在负相关性。(4)COVID-19患者生活质量的影响因素分析:多元线性回归分析显示,性别(β=8.27)、抑郁程度(β=-0.34)和疾病分型(β=-11.68)是患者SF-12V2生理总评分的重要决定因素(P<0.05);焦虑程度(β=-0.62)是患者SF-12V2心理总评分的重要决定因素(P<0.05)。结论:COVID-19出院患者存在呼吸困难、焦虑抑郁情绪和生活质量下降的问题;性别、疾病分型、抑郁程度和焦虑程度是COVID-19患者生活质量下降的重要因素。COVID-19患者(特别是女性患者和重型患者)出院后要尽早进行抑郁症和焦虑症的筛查和干预,减少患者负性情绪,鼓励患者适当参与康复训练,提高呼吸功能,从而促进生活质量提高。     

对比四维子宫输卵管超声造影与子宫输卵管造影评估输卵管通畅性效能:Meta分析

目的 采用Meta分析对比四维子宫输卵管超声造影（4D-HyCoSy）与子宫输卵管造影（HSG）评估输卵管通畅性的效能。方法 系统搜索PubMed、Cochrane Library、Embase、Web of Science、中国生物医学文献数据库、中国知网、万方医学网及维普数据库中建库至今有关4D-HyCoSy和/或HSG评估输卵管通畅性的文献。由2名研究人员依据纳入标准和排除标准筛选文献并提取信息；分别计算4D-HyCoSy和HSG评估输卵管通畅性的合并敏感度（SEN）、特异度（SPE）及诊断比值比（DOR），绘制综合受试者工作特征（SROC）曲线，获得曲线下面积（AUC），并以Medcalc 19.1.1统计软件比较AUC。结果 最终纳入19篇文献、1 358例疑似输卵管因素导致不孕患者，其中4篇同时采用4D-HyCoSy及HSG评估输卵管通畅性，10篇仅以4D-HyCoSy评估，5篇仅以HSG评估。Meta分析结果显示，4D-HyCoSy评估输卵管通畅性的合并SEN、SPE及DOR分别为0.92[95%CI（0.91，0.94）]、0.91[95%CI（0.89，0.93）]及115.06[95%CI（54.23，224.10）]；HSG评估输卵管通畅性的合并SEN、SPE及DOR分别为0.84[95%CI（0.81，0.87）]、0.80[95%CI（0.76，0.83）]及28.64[95%CI（10.08，81.35）]。4D-HyCoSy评估输卵管通畅性的AUC为0.98[95%CI（0.96，0.99）]，HSG为0.93[95%CI（0.90，0.95）]，差异有统计学意义（Z=6.97，P<0.01）。结论 4D-HyCoSy评估输卵管通畅性的效能高于HSG。     

脉络学说营卫理论指导心律失常辨证论治

经脉包括经(气)络和血(脉)络,清代周学海《读医随笔》将气络末端称为"气之细络",脉络末端称为"血之细络"。心之气络涵盖心脏起搏与传导系统等广泛调控机制,心之脉络涵盖冠状动脉循环系统,心之气络与脉络相互协调,营卫相偕而行,共同维持心脏正常功能。各种致病因素导致营卫异常而发为心律失常,基于脉络学说营卫理论"损其心者,调其营卫"(《难经·十四难》)治疗原则指导心律失常辨证论治,同时充分结合现代致病因素和致病特点,分别选用调节卫气营血之方药,标本兼治,以期为临床诊疗提供有益借鉴。