基于小波变换的心音包络提取算法及应用

背景:心音信号包含了大量心脏瓣膜活动的生理信息,心音分析对诊断心脏疾病具有重要的临床意义。目的:旨在通过心音的包络提取,分析心音信号的各种特征,进而判断心音中是否包含杂音,以改善传统听诊技术高度依赖医生经验、听诊范围受限的缺点。方法:提出了一种采用小波变换来提取心音包络的方法,通过与采用希尔伯特-黄变换、数学形态学、平均香农能量等心音包络求解方法进行对比,证明这种方法具有算法简便、曲线光滑、特征点突出等优点。结果与结论:将该方法用于临床真实心音的包络提取,利用支持向量机来训练所提取心音包络的面积和小波能量两个特征参数,判别心音信号是否明显包含杂音。选用35例心音数据对算法进行验证,结果表明该算法的准确率达到95%,具有很强的实用性。     

用谐波小波包变换法提取GIS局部放电信号多尺度特征参数

超高频(UHF)法在GIS局部放电(PD)检测中已得到了广泛应用，UHF PD信号的特征提取对准确识别GIS内部绝缘缺陷类型和指导检修工作具有重要意义，但目前仍然缺乏有效的特征提取方法。为此，本文利用谐波小波具有严格盒形频谱的优点，提出一种提取UHF PD特征信息的谐波小波包变换(HWPT)方法，对实验室获取的4种典型放电模型产生的UHF PD信号，采用HWPT进行多尺度分解，以克服实小波包分解子带间存在频谱混叠和能量泄漏的缺陷，利用UHF PD信号在不同尺度能量和复杂度的差异，提取多尺度能量和多尺度样本熵参数作为模式识别的特征量，更加精确地描述了UHF PD信号的时频域信息。最后利用支持向量机分类识别的结果表明，该方法可以取得比实小波包更好的识别效果，多尺度能量和多尺度样本熵特征参数均能有效识别4种绝缘缺陷。     

基于独立成分和小波分析的胎儿心电提取

背景：在胎儿心电信号的采集过程中,会受到母体和其他噪声的强干扰,如何快捷与有效地提取出胎儿心电将成为重要的研究课题。目的：采用结合独立成分分析和小波分析的方法对来自于同一母体的观测信号进行独立分量分离,得到有效的胎儿心电。方法：结合独立成分分析和小波分析的算法进行胎儿心电的特征提取,首先对含噪信号进行小波变换,去除奇异信号和非平稳随机信号,然后对小波重构后的信号运用快速独立成分分析算法进行成分分析。结果与结论：在胎儿心电信号的采集过程中,会受到母体和其他噪声的强干扰,但这些信号都是随机的,不相关的,可以认为它们间是相互独立的。采用结合独立成分和小波分析的方法对来自于同一母体的观测信号进行独立分量分离,得到有效的胎儿心电。实验证明该方法是一种有效的方法。     

结合小波变换对心电信号中RR间期检测的一种新方法

目的：探讨改善心电信号噪声干扰的方法，提高对心率变异信号中的RR间期检测精度。 方法：①采用国际上通用的MIT／BIH数据库作为研究心率变异信号中RR间期的研究对象，选取其中的代表性数据组进行实验分析（受严重基线漂移影响的正常心电信号101．dat，大量室性期前收缩的心电信号105．dat，无噪声干扰的正常心电信号213．dat，心动过速的心电信号217．dat）。②利用小波变化方法结合Mallat算法对含有噪声的心电信号进行多尺度分析和信号重构，并利用R波的自身波形特点，采用相对周期极大值法来进行R波位置检测，进而计算RR间期序列值。 结果：利用小波变换对含有噪声的信号进行噪声消除可以达到在很大程度保留原始信号的波形特征的同时又取得良好消噪效果的目的。能够显著减小工频干扰、基线漂移和肌电干扰等噪声对判别的影响。通过MIT／BIH数据库中四组有代表性特征的心电信号进行研究，发现采用相对周期极大值检测法可以显著减少检测中易出现的漏检和误检现象，快速而准确的获得RR间期的序列值。 结论：小波变换法能够显著减少噪声对信号的干扰，特别是离散小波的应用使数字信号的处理由理论走向实际，结合Mallat快速算法，使得小波变换完全走向实用化。周期极大值法对心率变异信号中RR间期的检测有较好的精确度和快速性。     

从体表电生理信号中提取希氏束信号的分析系统

背景:传统的希氏束检测方法是对体表心电信号进行数百次叠加或者经食道检测以及心内导管检测得到,研制从体表心电信号提取希氏束信号不但有利于临床诊断,也有利于动物药物实验.目的:从体表心电信号中提取希氏束信号,并开发体表希氏束信号分析系统.方法:以家兔体表心电信号作为待分析信号,以其心内希氏束电图作为对照信号,采用随机共振、小波变换、叠加平均和耦合累加等分析方法,对体表心电信号进行分析.结果与结论:小波变换后得到的信号,可以从体表心电信号中检测出希氏束信号,但并不是所有希氏束信号都能被识别,心内信号经过小波变换后,个别希氏束信号反而消失.随机共振方法从体表心电中检测出的希氏束信号识别率要高于小波分析方法,随机共振方法与小波分析相同之处是,心内信号经过处理后,个别希氏束信号反而消失.本文提出的耦合叠加算法能够从体表心电信号提取出希氏束信号,与经典叠加方法比较,其优点是希氏束信号明显,叠加次数远远少于经典叠加方法.提示实验采用的随机共振、小波变换、耦合累加等分析方法,能够有效抑制噪声、提取希氏束信号,开发研制的体表希氏束信号分析系统具有较强的实用价值.     

动脉导管未闭合并原发性房间隔膨胀瘤的超声诊断

患者,女,24岁.1孕、16周,因感心慌乏力来我院就诊.心脏听诊:心率105次/分,律齐,各听诊区均闻及病理性杂音,第二心音亢进分裂.胸部X线显示,主动脉结明显抬高,左心缘向左下延伸、增大,心界不清.     

超声诊断房间隔膨胀瘤伴缺损及多囊肝、多囊肾1例

患者男,34岁。因胸闷、心慌、乏力、活动后加重4个月来院就诊。有多囊肝、多囊肾家族史。查体：一般状况好,胸廓未见畸形,心前区未见隆起。心脏听诊：心率56次/分,节律整,于胸骨左缘二、三肋间可闻及Ⅲ级收缩期杂音,肺动脉瓣区第二心音亢进分裂。心电图示：窦性心动过缓;完全性右束支传导阻滞;右心室肥大。     

基于支持向量机研究肌肉多运动模式识别

针对传统神经网络模式识别率低、收敛速度慢等缺点,提出用支持向量机处理表面肌电信号。采用小波变换对表面肌电信号进行分析,提取小波变换系数的标准方差作为表面肌电信号特征;随后引入支持向量机对肌肉进行展拳、握拳、腕外旋、腕内旋等4种动作模式分类。实验表明,用小波变换的标准方差所提取的表面肌电信号特征作为支持向量机模式分类器的输入,用于识别动作模式,具有运行速度快,识别率高,鲁棒性好的特点。     

听诊误诊心血管疾病4例分析

听诊对于心血管疾病诊断具有重要意义。本文就听诊失误而发生的器质性心血管疾病4例长期误诊作一分析,从中吸取教训。病例一:男性,51岁。因咳嗽、咳痰、咯血和呼吸困难在门诊治疗十余年,长期被诊为慢性支气管炎、肺气肿、慢性肺原性心脏病。既往常有感冒、咽峡炎。入院后发现手足发绀,上腹部有搏动,混合性呼吸困难,肺部听到干湿性罗音。心脏听诊:平卧时心尖区第一心音增强和收缩期杂音,肺动脉瓣区第二音亢进;左侧卧呼气末,特别是轻微活动后,心尖区第一心音呈典型的拍击样,心尖区还可听到一舒张中期伴有收缩期前增强的粗糙杂音,用仪器     

正常儿童心脏杂音与心脏瓣膜返流的临床观察

目的探讨正常儿童心脏轻度杂音与心脏瓣膜返流的相关性。方法选取2001年3月至2007年8月本院儿科保健门诊3月至6岁938例儿童进行健康体检跟踪观察（排除体检中确诊为先天性心脏病的患儿）。杂音组：23例心脏听诊轻度杂音。对照组：30例心脏听诊无杂音。均行心电图、心脏超声检查。结果正常儿童心脏轻度杂音发生率2．452％（23／938）。轻度杂音与三尖瓣轻度返流高度相关，其次是二尖瓣返流。随年龄增加逐步改善。结论正常儿童心脏轻度杂音与心脏瓣膜返流高度相关，随年龄增加无不适情况出现，属良性改变。     

Classification of surface EMG signals using harmonic wavelet packet transform

In this paper, an efficient method based on the discrete harmonic wavelet packet transform (DHWPT) is presented to classify surface electromyographic (SEMG) signals. After the relative energy of SEMG signals in each frequency band had been extracted by the DHWPT, a genetic algorithm was utilized to select appropriate features in order to reduce the feature dimensionality. Then, the selected features were used as the input vectors to a neural network classifier to discriminate four types of prosthesis movements. Compared with other classification methods, the proposed method provided high classification accuracy in experimental research. In addition, this method could also save a lot of computational time because the DHWPT has a fast algorithm based on the fast Fourier transform for numerical implementation.     

Representation and classification of breath sounds recorded in an intensive care setting using neural networks

Objective.Develop and test methods for representing and classifying breath sounds in an intensive care setting. Methods.Breath sounds were recorded over the bronchial regions of the chest. The breath sounds were represented by their averaged power spectral density, summed into feature vectors across the frequency spectrum from 0 to 800 Hertz. The sounds were segmented by individual breath and each breath was divided into inspiratory and expiratory segments. Sounds were classified as normal or abnormal. Different back-propagation neural network configurations were evaluated. The number of input features, hidden units, and hidden layers were varied.Results.2127 individual breath sounds from the ICU patients and 321breaths from training tapes were obtained. Best overall classification rate for the ICU breath sounds was 73% with 62% sensitivity and 85% specificity. Best overall classification rate for the training tapes was 91% with 87%sensitivity and 95% specificity. Conclusions.Long term monitoring of lung sounds is not feasible unless several barriers can be overcome. Several choices in signal representation and neural network design greatly improved the classification rates of breath sounds. The analysis of transmitted sounds from the trachea to the lung is suggested as an area for future study. This revised version was published online in July 2006 with corrections to the Cover Date.     

Artifact reduction in magnetogastrography using fast independent component analysis

The analysis of magnetogastrographic (MGG) signals has been limited to epochs of data with limited interference from extraneous signal components that are often present and may even dominate MGG data. Such artifacts can be of both biological (cardiac, intestinal and muscular activities, motion artifacts, etc) and non-biological (environmental noise) origin. Conventional methods-such as Butterworth and Tchebyshev filters-can be of great use, but there are many disadvantages associated with them as well as with other typical filtering methods because a large amount of useful biological information can be lost, and there are many trade-offs between various filtering methods. Moreover, conventional filtering cannot always fully address the physicality of the signal-processing problem in terms of extracting specific signals due to particular biological sources of interest such as the stomach, heart and bowel. In this paper, we demonstrate the use of fast independent component analysis (FICA) for the removal of both biological and non-biological artifacts from multi-channel MGG recordings acquired using a superconducting quantum intereference device (SQUID) magnetometer. Specifically, we show that the signal of gastric electrical control activity (ECA) can be isolated from SQUID data as an independent component even in the presence of severe motion, cardiac and respiratory artifacts. The accuracy of the method is analyzed by comparing FICA-extracted versus electrode-measured respiratory signals. It is concluded that, with this method, reliable results may be obtained for a wide array of magnetic recording scenarios.     

Analysis of surface EMG signal morphology in Parkinson's disease

A novel approach is presented for the analysis of surface electromyogram (EMG) morphology in Parkinson's disease (PD). The method is based on histogram and crossing rate (CR) analysis of the EMG signal. In the method, histograms and CR values are used as high-dimensional feature vectors. The dimensionality of them is then reduced using the Karhunen-Loève transform (KLT). Finally, the discriminant analysis of feature vectors is performed in low-dimensional eigenspace. Histograms and CR values were chosen for analysis, because Parkinsonian EMG signals typically involve patterns of EMG bursts. Traditional methods of EMG amplitude and spectral analysis are not effective in analyzing impulse-like signals. The method, which was tested with EMG signals measured from 25 patients with PD and 22 healthy controls, was promising for discriminating between these two groups of subjects. The ratio of correct discrimination by augmented KLT was 86% for the control group and 72% for the patient group. On the basis of these results, further studies are suggested in order to evaluate the usability of this method in early stage diagnostics of PD.     

Looking is not seeing and listening is not hearing: effect of an intervention to enhance auditory skills of graduate-entry nursing students

Inspection/observation and listening/auscultation are essential skills for health care providers. Given that observational and auditory skills take time to perfect, there is concern about accelerated students' ability to attain proficiency in a timely manner. This article describes the impact of music auditory training (MAT) for nursing students in an accelerated master's entry program on their competence in detecting heart, lung, and bowel sounds. During the first semester, a two-hour MAT session with focused attention on pitch, timbre, rhythm, and masking was held for the intervention group; a control group received traditional instruction only. Students in the music intervention group demonstrated significant improvement in hearing bowel, heart, and lung sounds (p < .0001). The ability to label normal and abnormal heart sounds doubled; interpretation of normal and abnormal lung sounds improved by 50 percent; and bowel sounds interpretation improved threefold, demonstrating the effect of an adult-oriented, creative, yet practical method for teaching auscultation.     

Analysis of the spectral envelope of sounds by the human brain

Spectral envelope is the shape of the power spectrum of sound. It is an important cue for the identification of sound sources such as voices or instruments, and particular classes of sounds such as vowels. In everyday life, sounds with similar spectral envelopes are perceived as similar: we recognize a voice or a vowel regardless of pitch and intensity variations, and we recognize the same vowel regardless of whether it is voiced (a spectral envelope applied to a harmonic series) or whispered (a spectral envelope applied to noise). In this functional magnetic resonance imaging (fMRI) experiment, we investigated the basis for analysis of spectral envelope by the human brain. Changing either the pitch or the spectral envelope of harmonic sounds produced similar activation within a bilateral network including Heschl's gyrus and adjacent cortical areas in the superior temporal lobe. Changing the spectral envelope of continuously alternating noise and harmonic sounds produced additional right-lateralized activation in superior temporal sulcus (STS). Our findings show that spectral shape is abstracted in superior temporal sulcus, suggesting that this region may have a generic role in the spectral analysis of sounds. These distinct levels of spectral analysis may represent early computational stages in a putative anteriorly directed stream for the categorization of sound.     

Regional heart motion abnormality detection: An information theoretic approach

Tracking regional heart motion and detecting the corresponding abnormalities play an essential role in the diagnosis of cardiovascular diseases. Based on functional images, which are subject to noise and segmentation/registration inaccuracies, regional heart motion analysis is acknowledged as a difficult problem and, therefore, incorporation of prior knowledge is desirable to enhance accuracy. Given noisy data and a nonlinear dynamic model to describe myocardial motion, an unscented Kalman smoother is proposed in this study to estimate the myocardial points. Due to the similarity between the statistical information of normal and abnormal heart motions, detecting and classifying abnormality is a challenging problem. We use the Shannon’s differential entropy of the distributions of potential classifier features to detect and locate regional heart motion abnormality. A naive Bayes classifier algorithm is constructed from the Shannon’s differential entropy of different features to automatically detect abnormal functional regions of the myocardium. Using 174 segmented short-axis magnetic resonance cines obtained from 58 subjects (21 normal and 37 abnormal), the proposed method is quantitatively evaluated by comparison with ground truth classifications by radiologists over 928 myocardial segments. The proposed method performed significantly better than other recent methods, and yielded an accuracy of 86.5% (base), 89.4% (mid-cavity) and 84.5% (apex). The overall classification accuracy was 87.1%. Furthermore, standard kappa statistic comparisons between the proposed method and visual wall motion scoring by radiologists showed that the proposed algorithm can yield a kappa measure of 0.73.     

MRI图像的小波融合处理

背景：小波图像融合是将两幅图像融合在一起,以获取对同一场景的更为精确、全面、可靠的图像描述。目的：用小波变换图像融合技术融合MRI脑梗死图像,以恢复缺损图像。方法：图像融合的主要机制是利用二维小波分析法对MRI脑梗死图像进行小波分解,并对高低频信号采用多种融合方式进行融合。通过对比不同融合方式后的效果图,找出最适合本部位MRI图像的融合方法。结果与结论：不同方式的融合技术能成功修复不同的缺损部位,多种融合方式的合适组合能完全修复多处缺失部位。对于文中给出的MRI脑梗死图像,采用最小值融合方式的融合效果最好。提示使用二维小波分析法处理医学图像,简便快捷,能有效改善图像的视觉效果,辅助临床诊断。