Pneumocystis carnii pneumonia in AIDS--an autopsy report

Pneumocystis carinii pneumonia (PCP), the most common presenting manifestation in patients with AIDS from western countries, holds the distinction for being the first opportunistic infection that was associated with AIDS. There is marked paucity of clinically diagnosed and pathologically confirmed cases of PCP in India. This case represents the first complete autopsy report of pneumocystis carinii pneumonia inpatient with AIDS from our country. A high index of clinical suspicion and microscopic confirmation is needed to avert mortality due to PCP in patients with AIDS.     

A proposal for a classification system of enuresis based on overnight simultaneous monitoring of electroencephalography and cystometry

A classification system of enuresis was proposed based on the overnight simultaneous electroencephalographic (EEG) and cystometric (CM) monitoring of 204 cases. The classification types proposed were as follows: (a) Type I (125 cases, 61%). The first bladder contraction (FBC) in CM is noticed on cystometrogram (CMG) during Stage 4 sleep when the bladder is full. An evidence of arousals in EEG appears and EEG changes to a Stage 1 or 2 sleep pattern; however, enuresis occurs without waking. (b) Type IIa (22 cases, 11%). FBC is noticed as in Type I, but no EEG response is observed; enuresis occurs. (c) Type IIb (57 cases, 28%). An uninhibited contraction of the bladder is observed on CMG only during sleep (not on awakening). No change in either FBC or EEG is found, but enuresis occurs. It is expected that new methods of treatment for enuresis will be developed based on this classification system.     

基于离散小波变换提取脑机接口中脑电特征

在脑机接口中，针对脑电特征提取利用单一种类信息、使用数据量大、分类性能较差等缺点，提出一种新颖的基于离散小波变换的方法。分析了小波变换特征提取的特点和特征表示方式，用Daubechies类db4小波函数对脑电信号进行6层分解，抽取小波变换各子带关键的部分逼近系数、小波系数、小波子带系数均值组成特征向量。以分类正确率为指标检验了提取特征的性能。实验结果表明，这种方法能够利用少量数据提取脑电信号本质特征，具有较高的分类性能，为利用脑电识别人的不同意图提供了快速而有效的手段。     

基于ABC-SVM的运动想象脑电信号模式分类

为了提高运动想象脑电信号分类的准确率,针对传统支持向量机（SVM）分类方法在脑电信号处理中存在寻优繁 琐、工作量大和分类正确率低等问题,本研究提出一种基于人工蜂群（ABC）算法优化SVM的分类识别方法。首先利用正 则化共空间模式对脑电信号进行特征提取,然后利用ABC算法优化SVM的惩罚因子和核参数,最后利用提取的右手和 右脚两类脑电信号样本特征对优化后的SVM进行训练和分类测试。实验结果表明ABC-SVM分类器提高了脑电信号分 类的准确率,比传统的SVM分类器准确率高出2.5%,证明该算法的可行性和较高准确性。     

癫痫发作脑电信号的相位幅度调制研究

脑电图是癫痫诊治中一种最为重要的工具,而大数据量的脑电记录给人工分析带来困难,计算机分类则可减轻此负担。从相位幅度调制角度研究癫痫脑电低频节律相位与高频节律幅度间的耦合关系,利用归一化后的调制指数(MI)来量化各频段间的耦合强度。基于波恩癫痫发作间期和发作期脑电的200个样本数据集,提出依据高低频节律范围对MI图进行分区,再利用分区后的耦合系数对不同状态下的脑电进行分类。结果显示,发作期Gamma节律与Delta(2～4 Hz)节律的MI值(0.009 9±0.009 6)相比发作间期(0.003 6±0.008 7)显著增加(P<0.01)。Gamma节律与Theta(4～8 Hz)节律的发作期MI值(0.008 7±0.006 2)相比发作间期(0.001 4±0.003 2)也有显著增加(P<0.01);Theta Beta节律间耦合强度在发作期(0.002 2±0.001 3)与发作间期(0.000 5±0.000 7)也存在显著差异。利用支持向量机在五折交叉验证下,波恩癫痫脑电数据MI特征对发作期和间期数据分类准确率达到97%;采用随机森林分类方法,同样得到一致结果。所提出方法的应用可有效提高对临床视频脑电图分析的效率。     

利用整体经验模态分解和随机森林的脑电信号分类研究

癫痫脑电信号的自动监测与分类在临床医学上具有重要意义。针对脑电信号的非平稳特点,提出一种基于整体经验模态分解和随机森林相结合的脑电信号分类方法。选取波恩大学脑电信号数据集中癫痫发作间期和发作期的200个单通道信号,共819 400个数据作为样本。首先利用整体模态分解将癫痫脑电信号分解成多个固有模态函数,然后对各阶固有模态函数提取有效特征,最后分别用随机森林和最小二乘支持向量机对脑电信号的特征进行分类。将随机森林与最小二乘支持向量机分类正确识别率对比,结果表明,随机森林分类方法对发作期和发作间期的癫痫脑电信号的分类效果比较理想,识别精度为99.60％,高于最小二乘支持向量机的准确性。该方法的提出能有效提高临床癫痫脑电信号分析的效率。     

儿童癫癎发作的临床特征与录像脑电图分析

目的：分析儿童癫痫发作的临床表现和录像脑电图(Video—EEG)特征。方法：对123例年龄9天至15岁癫痫患儿进行Video—EEG监测，记录并同步分析发作时EEG与临床表现。结果：123例中记录到568次发作，分三种类型。1、全面性发作53例201次发作：①婴儿痉挛18例中53次发作，发作期EEG表现为广泛低波幅快活动或高波幅慢波暴发与低电压抑制；②肌阵挛发作12例中79次发作，发作期EEG表现各导联多棘波、多棘慢波；③强直发作10例中24次发作，发作期EEG表现导联低波幅快节律、多棘慢波；④阵挛发作10例中39次发作，发作期EEG表现各导联棘慢波、尖慢波；⑤失神发作3例中6次发作，发作期EEG表现全导联3Hz棘慢波。2、部分性发作67例中339次发作．分别起源于额、中央、顶、颞、枕，其中38例191次发作为继发全身发作。3、混合发作3例中28次发作。结论：Video—EEG有助于临床医师对儿童癫痫的正确分型及指导治疗。     

多发性抽动症的临床与脑电图特征分析

目的：探讨多发性抽动症（tourette syndrome,TS）的临床及脑电图（EEG）特征。方法：对164例多发性抽动症患儿的临床及脑电图资料进行回顾性分析。结果：EEG异常36例,异常率22％,其中32例表现为枕区基本节律慢化,α波指数减少,α波调节调幅不良,阵发高幅θ节律等非特异性异常。另4例表现为典型的癫痫样放电。结论：部分TS患儿有EEG的异常改变,且EEG的异常与病程的长短及严重程度存在一定的对应关系,EEG可作为评估病变严重程度的客观依据之一。     

基于自回归模型和关联向量机的癫痫脑电信号自动分类

癫痫脑电信号自动分类方法的研究具有重要意义.基于自回归模型和关联向量机,实现癫痫脑电信号的自动分类.采用自回归模型,进行脑电信号特征提取;通过引入主成分分析和线性判别分析两种特征变换方法,降低特征空间维数;采用关联向量机作为分类器,提高模型稀疏性并可以得到概率式输出.在对波恩大学癫痫研究中心脑电信号的分类中,所提出的方法最高准确率可以达到99.875％;在将特征空间维数降至原始维数的1/15时,分类准确率仍可达到99.500％;采用关联向量机作为分类器,模型稀疏性大幅提高,与支持向量机相比,同等条件下关联向量数仅为支持向量数的几十分之一.所提方法可以很好地应用于癫痫脑电信号的自动分类.     

睡眠脑波调制的与常规的重复经颅磁刺激治疗原发性失眠症的脑电图研究

目的：探讨睡眠脑波调制重复经颅磁刺激与常规重复经颅磁刺激在治疗原发性失眠症中的脑电图（EEG）动态特征及其与临床疗效的关系。方法：按完全随机的方法,将126例原发性失眠症患者分为睡眠脑波调制重复经颅磁刺激组（睡磁组）44例、常规重复经颅磁刺激组（常磁组）42例和假磁刺激治疗组（假磁组）40例。每次持续刺激30min,每日1次,疗程10d。分别观察治疗前、治疗10d时和治疗结束后30d时的Krakow睡眠积分（KSS）、EEG及平均α波绝对功率谱的变化。结果：两磁疗组治疗10d时的KSS显著降低（均P〈0．05）,平均α波绝对功率谱显著升高（均P〈0．05）,尤以睡磁组突出,且持续至治疗结束后30d。治疗10d时磁疗患者平均α波绝对功率谱与其KSS呈显著负相关（n=86,r=0．2136,P〈0．05）。结论：睡眠脑波调制重复经颅磁刺激和常规重复经颅磁刺激对原发性失眠症的异常EEG均有显著的良性调节作用,其疗效与提高平均α波功率谱相关,前者优于后者。     

Epileptic seizure detection using DWT-based approximate entropy,Shannon entropy and support vector machine: a case study

In this work, we have used a time–frequency domain analysis method called discrete wavelet transform (DWT) technique. This method stand out compared to other proposed methods because of its algorithmic elegance and accuracy. A wavelet is a mathematical function based on time-frequency analysis in signal processing. It is useful particularly because it allows a weak signal to be recovered from a noisy signal without much distortion. A wavelet analysis works by analysing the image and converting it to mathematical function which is decoded by the receiver. Furthermore, we have used Shannon entropy and approximate entropy (ApEn) for extracting the complexities associated with electroencephalographic (EEG) signals. The ApEn is a suitable feature to characterise the EEGs because its value drops suddenly due to excessive synchronous discharge of neurons in the brain during epileptic activity in this study. EEG signals are decomposed into six EEG sub-bands namely D1–D5 and A5 using DWT technique. Non-linear features such as ApEn and Shannon entropy are calculated from these sub-bands and support vector machine classifiers are used for classification purpose. This scheme is tested using EEG data recorded from five healthy subjects and five epileptic patients during the inter-ictal and ictal periods. The data are acquired from University of Bonn, Germany. The proposed method is evaluated through 15 classification problems, and obtained high classification accuracy of 100% for two cases and it indicates the good classifying performance of the proposed method.     

急性毒鼠强中毒的脑电图分析

目的:探讨急性毒鼠强中毒时脑电图的变化及与临床的关系。方法:对13例急性毒鼠强中毒的脑电图进行回顾性分析及随访。结果:13例患者中正常范围内脑电图1例,轻度异常脑电图2例,均为轻度中毒患者。这2例患者的脑电图在一周后复查时恢复正常范围。5例中度异常脑电图均为中度中毒患者,在一周后复查时4例脑波恢复α波,但仍有较多量的θ波,复型慢波及阵发性尖波消失。另1例为6-7Hz的θ波,并仍有少量的复型慢波及阵发性尖波。5例重度异常脑电图其中4例为重度中毒患者,1例为中度中毒患者。第一次复查时脑波虽有改善但仍可见复型慢波及阵发性高幅尖波。这10例中一重度异常脑电图的患者在3月后第二次复查时,其中8例脑电图恢复正常范围,另2例脑波虽恢复到8-9Hz的α波,但仍有较多量的θ波及少量的复型慢波,阵发性尖波消失。结论:毒鼠强中毒患者脑电图的异常程度与中毒程度及临床症状相一致。其动态变化可反映病情的转归。提示脑电图检查可反映脑损害的程度,可为临床诊断,预后,评估提供依据。     

基于迁移学习和空洞卷积的癫痫状态识别方法

癫痫患者脑电信号的自动检测和发作诊断对临床治疗癫痫具有重要意义。针对训练数据有限及训练与测试数据分布不一致的难点,采用领域间联合知识迁移学习方法,实现小训练数据量下的癫痫状态识别。首先对脑电信号进行4层小波包分解,提取小波包分解系数作为特征,通过边缘分布和联合分布迭代调整,完成源域和目标域特征之间的知识迁移,训练空洞卷积神经网络作为分类器,完成目标域癫痫状态识别。分别在波士顿儿童医院CHB-MIT脑电数据集(22 例被试,共计790 h)和波恩大学癫痫脑电数据集(5 组,每组100 个片段,每段23.6 s)上进行算法验证,实验结果表明,所提出的方法对复杂癫痫状态的平均识别准确度、敏感性、特异性在CHB-MIT数据集上达到96.8％、96.1％、96.4％;在波恩数据集上,平均识别准确率为96.9%,有效提高了癫痫状态识别综合性能,实现了癫痫发作稳定可靠检测。     

Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification

We introduce a new adaptive time-frequency plane feature extraction strategy for the segmentation and classification of electroencephalogram (EEG) corresponding to left and right hand motor imagery of a brain-computer interface task. The proposed algorithm adaptively segments the time axis by dividing the EEG data into non-uniform time segments over a dyadic tree. This is followed by grouping the expansion coefficients in the frequency axis in each segment. The most discriminative features are selected from the segmented time-frequency plane and fed to a linear discriminant for classification. The proposed algorithm achieved an average classification accuracy of 84.3% on six subjects by selecting the most discriminant subspaces for each one. For comparison, classification results based on an autoregressive model are also presented where the mean accuracy of the same subjects turned out to be 79.5%. Interestingly the subjects and two hemispheres of each subject are represented by distinct segmentations and features. This indicates that the proposed method can handle inter-subject variability when constructing brain-computer interfaces.     

Wavelet-based sparse functional linear model with applications to EEGs seizure detection and epilepsy diagnosis

In epilepsy diagnosis or epileptic seizure detection, much effort has been focused on finding effective combination of feature extraction and classification methods. In this paper, we develop a wavelet-based sparse functional linear model for representation of EEG signals. The aim of this modeling approach is to capture discriminative random components of EEG signals using wavelet variances. To achieve this goal, a forward search algorithm is proposed for determination of an appropriate wavelet decomposition level. Two EEG databases from University of Bonn and University of Freiburg are used for illustration of applicability of the proposed method to both epilepsy diagnosis and epileptic seizure detection problems. For this data considered, we show that wavelet-based sparse functional linear model with a simple classifier such as 1-NN classification method leads to higher classification results than those obtained using other complicated methods such as support vector machine. This approach produces a 100 % classification accuracy for various classification tasks using the EEG database from University of Bonn, and outperforms many other state-of-the-art techniques. The proposed classification scheme leads to 99 % overall classification accuracy for the EEG data from University of Freiburg.     

A Comparative Study of Different EEG Reference Choices for Diagnosing Unipolar Depression

The choice of an electroencephalogram (EEG) reference has fundamental importance and could be critical during clinical decision-making because an impure EEG reference could falsify the clinical measurements and subsequent inferences. In this research, the suitability of three EEG references was compared while classifying depressed and healthy brains using a machine-learning (ML)-based validation method. In this research, the EEG data of 30 unipolar depressed subjects and 30 age-matched healthy controls were recorded. The EEG data were analyzed in three different EEG references, the link-ear reference (LE), average reference (AR), and reference electrode standardization technique (REST). The EEG-based functional connectivity (FC) was computed. Also, the graph-based measures, such as the distances between nodes, minimum spanning tree, and maximum flow between the nodes for each channel pair, were calculated. An ML scheme provided a mechanism to compare the performances of the extracted features that involved a general framework such as the feature extraction (graph-based theoretic measures), feature selection, classification, and validation. For comparison purposes, the performance metrics such as the classification accuracies, sensitivities, specificities, and F scores were computed. When comparing the three references, the diagnostic accuracy showed better performances during the REST, while the LE and AR showed less discrimination between the two groups. Based on the results, it can be concluded that the choice of appropriate reference is critical during the clinical scenario. The REST reference is recommended for future applications of EEG-based diagnosis of mental illnesses.     

偏执型精神分裂症病人与正常人脑电图向量分析

目的 :用向量分析法处理脑电图 ,为脑电图研究提供一个新的手段。方法 :将 94例偏执型精神分裂症病人 (病人组 )与 35例正常人 (对照组 )的脑电向量分析结果进行比较。结果 :病人组中 6 9例异常 ,2 5例正常。对照组中 ,1例异常 ,34例正常。结论 :脑电信息流的向量分析技术 ,对精神病人的临床诊断有重要价值。     

Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines

A new approach based on the implementation of multiclass support vector machine (SVM) with the error correcting output codes (ECOC) is presented for classification of electroencephalogram (EEG) signals. In practical applications of pattern recognition, there are often diverse features extracted from raw data which needs recognizing. Decision making was performed in two stages: feature extraction by eigenvector methods and classification using the classifiers trained on the extracted features. The aim of the study is classification of the EEG signals by the combination of eigenvector methods and multiclass SVM. The purpose is to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. The present research demonstrated that the eigenvector methods are the features which well represent the EEG signals and the multiclass SVM trained on these features achieved high classification accuracies.     

Reproducibility of new classification schemes for the pathology of ductal carcinoma in situ of the breast.

AIM: To compare the interobserver variation in the pathological classification of ductal carcinoma in situ of the breast using two recently proposed classification schemes. METHODS: 11 pathologists classified a set of 25 cases of ductal carcinoma in situ chosen to reflect a range of lesions, using the traditional architectural classification together with the modified cytonuclear grading scheme of Holland et al and the Van Nuys classification scheme. Participating pathologists received a standard tutorial, written information, and illustrative photomicrographs before their assessment of the cases. RESULTS: Interobserver agreement was poorest when using the architectural scheme (kappa = 0.44), largely owing to variations in classifying lesions with a mixed component of patterns (kappa = 0.13). Agreement was better using the modified cytonuclear grading scheme (kappa = 0.57), with most consistency achieved using the Van Nuys scheme (kappa = 0.66). Most discordant results using the later scheme were due to inconsistency in assessing the presence or absence of luminal necrosis. CONCLUSIONS: Both the new classification schemes assessed in this study were an improvement over the traditional architectural classification system for ductal carcinoma in situ, and resulted in more reproducible pathological assignment of cases. The Van Nuys classification scheme is easy to apply, even to small areas of carcinoma, resulting in acceptable interobserver agreement between reporting pathologists. Additional work will be required to arrive at a consensus definition of necrosis for cases in the non-high-grade group.     

Relationship of genetically transmitted alpha EEG traits to anxiety disorders and alcoholism

We tested the hypothesis that a heritable EEG trait, the low voltage alpha (LV), is associated with psychiatric disorders. Modest to moderate evidence for genetic linkage of both panic disorder and the low voltage alpha trait to the same region of chromosome 20q has recently been reported, raising the issue of whether there is a phenotypic correlation between these traits. A total of 124 subjects including 50 unrelated index subjects and 74 relatives were studied. Alpha EEG power was measured and EEG phenotypes were impressionistically classified. Subjects were psychiatrically interviewed using the SADS-L and blind-rated by RDC criteria. Alcoholics were four times more likely to be LV (including so-called borderline low voltage alpha) than were nonalcoholic, nonanxious subjects. Alcoholics with anxiety disorder are 10 times more likely to be LV. However, alcoholics without anxiety disorder were similar to nonalcoholics in alpha power. An anxiety disorder (panic disorder, phobia, or generalized anxiety) was found in 14/17 LV subjects as compared to 34/101 of the rest of the sample (P < 0.01). Support for these observations was found in the unrelated index subjects in whom no traits would be shared by familial clustering. Lower alpha power in anxiety disorders was not state-dependent, as indicated by the Spielberger Anxiety Scale. Familial covariance of alpha power was 0.25 (P < 0.01). These findings indicate there may be a shared factor underlying the transmissible low voltage alpha EEG variant and vulnerability to anxiety disorders with associated alcoholism. This factor is apparently not rare, because LV was found in approximately 10% of unrelated index subjects and 5% of subjects free of alcoholism and anxiety disorders. © 1995 Wiley-Liss, Inc.