Microarray data classification based on ensemble independent component selection

Independent component analysis (ICA) has been widely deployed to the analysis of microarray datasets. Although it was pointed out that after ICA transformation, different independent components (ICs) are of different biological significance, the IC selection problem is still far from fully explored. In this paper, we propose a genetic algorithm (GA) based ensemble independent component selection (EICS) system. In this system, GA is applied to select a set of optimal IC subsets, which are then used to build diverse and accurate base classifiers. Finally, all base classifiers are combined with majority vote rule. To show the validity of the proposed method, we apply it to classify three DNA microarray data sets involving various human normal and tumor tissue samples. The experimental results show that our ensemble method obtains stable and satisfying classification results when compared with several existing methods.     

Extraction of cognitive activity-related waveforms from functional near-infrared spectroscopy signals

We address the problem of prototypical waveform extraction in cognitive experiments using functional near-infrared spectroscopy (fNIRS) signals. These waveform responses are evoked with visual stimuli provided in an oddball type experimental protocol. As the statistical signal-processing tool, we consider the linear signal space representation paradigm and use independent component analysis (ICA). The assumptions underlying ICA is discussed in the light of the signal measurement and generation mechanisms in the brain. The ICA-based waveform extraction is validated based both on its conformance to the parametric brain hemodynamic response (BHR) model and to the coherent averaging technique. We assess the intra-subject and inter-subject waveform and parameter variability.     

Entropy-based automated classification of independent components separated from fMCG

Fetal magnetocardiography (fMCG) is a noninvasive technique suitable for the prenatal diagnosis of the fetal heart function. Reliable fetal cardiac signals can be reconstructed from multi-channel fMCG recordings by means of independent component analysis (ICA). However, the identification of the separated components is usually accomplished by visual inspection. This paper discusses a novel automated system based on entropy estimators, namely approximate entropy (ApEn) and sample entropy (SampEn), for the classification of independent components (ICs). The system was validated on 40 fMCG datasets of normal fetuses with the gestational age ranging from 22 to 37 weeks. Both ApEn and SampEn were able to measure the stability and predictability of the physiological signals separated with ICA, and the entropy values of the three categories were significantly different at p <0.01. The system performances were compared with those of a method based on the analysis of the time and frequency content of the components. The outcomes of this study showed a superior performance of the entropy-based system, in particular for early gestation, with an overall ICs detection rate of 98.75% and 97.92% for ApEn and SampEn respectively, as against a value of 94.50% obtained with the time-frequency-based system.     

Applicability of independent component analysis on high-density microelectrode array recordings

Emerging complementary metal oxide semiconductor (CMOS)-based, high-density microelectrode array (HD-MEA) devices provide high spatial resolution at subcellular level and a large number of readout channels. These devices allow for simultaneous recording of extracellular activity of a large number of neurons with every neuron being detected by multiple electrodes. To analyze the recorded signals, spiking events have to be assigned to individual neurons, a process referred to as "spike sorting." For a set of observed signals, which constitute a linear mixture of a set of source signals, independent component (IC) analysis (ICA) can be used to demix blindly the data and extract the individual source signals. This technique offers great potential to alleviate the problem of spike sorting in HD-MEA recordings, as it represents an unsupervised method to separate the neuronal sources. The separated sources or ICs then constitute estimates of single-neuron signals, and threshold detection on the ICs yields the sorted spike times. However, it is unknown to what extent extracellular neuronal recordings meet the requirements of ICA. In this paper, we evaluate the applicability of ICA to spike sorting of HD-MEA recordings. The analysis of extracellular neuronal signals, recorded at high spatiotemporal resolution, reveals that the recorded data cannot be modeled as a purely linear mixture. As a consequence, ICA fails to separate completely the neuronal signals and cannot be used as a stand-alone method for spike sorting in HD-MEA recordings. We assessed the demixing performance of ICA using simulated data sets and found that the performance strongly depends on neuronal density and spike amplitude. Furthermore, we show how postprocessing techniques can be used to overcome the most severe limitations of ICA. In combination with these postprocessing techniques, ICA represents a viable method to facilitate rapid spike sorting of multidimensional neuronal recordings.     

Integrated MEG/fMRI Model Validated Using Real Auditory Data

The main objective of this paper is to present methods and results for the estimation of parameters of our proposed integrated magnetoencephalography (MEG) and functional magnetic resonance imaging (fMRI) model. We use real auditory MEG and fMRI datasets from 7 normal subjects to estimate the parameters of the model. The MEG and fMRI data were acquired at different times, but the stimulus profile was the same for both techniques. We use independent component analysis (ICA) to extract activation-related signal from the MEG data. The stimulus-correlated ICA component is used to estimate MEG parameters of the model. The temporal and spatial information of the fMRI datasets are used to estimate fMRI parameters of the model. The estimated parameters have reasonable means and standard deviations for all subjects. Goodness of fit of the real data to our model shows the possibility of using the proposed model to simulate realistic datasets for evaluation of integrated MEG/fMRI analysis methods.     

多通道局部场电位独立分量能量编码工作记忆事件的研究

目的 基于大鼠前额叶皮层多通道局部场电位（LFPs）的独立分量分析（ICA）,研究LEPs的各个独立分量（ICs）的能量如何编码工作记忆过程中的事件.方法 以事件发生点为零点,分别将±500 ms内在大鼠记忆皮层记录的15通道LEPs,通过ICA分解为15个ICs,计算各分量在窗宽为50 ms的窗口内的能量.以步长为25ms移动窗口,获得15个ICs能量的动态分布.选择在±200 ms内能量明显增高（即其能量改变编码了事件）的ICs,通过ICA逆变换可知ICs对应的记录通道.结果 在对同一段实验数据进行多次重复分析时,由于ICA算法分解结果的不确定性,在±200 ms内能量明显增高的ICs不尽相同,但其对应的空间位置均为同一通道处,表明该通道所在位置即为LFPs编码该次事件的主要功能区域;而对多段实验数据的分析结果显示,实验数据与分析所得的主要功能区域具有较为理想的一一对应性.结论 多通道LFPs独立分量的能量可以编码工作记忆过程中的事件;ICA对于识别多通道LFPs对工作记忆事件的编码模式是有效的;ICA可以对编码事件的主要功能区域进行空间定位,且鲁棒性较为理想.     

Spatial filters based on independent component analysis for magnetic noise reduction in the magnetocardiogram

A spatial filter design method to reduce magnetic noise in the magnetocardiogram (MCG) is introduced. Based on the facts that external magnetic noise appearing on multichannel MCG sensors is independent of the cardiac signals and that there is strong spatial correlation among the channels, the independent component analysis (ICA) method was applied to extract the noise components from the measured MCG signals. After extraction of the noise components in a given time period using ICA, a spatial filter was made to reduce the noise components in subsequently acquired MCG signals. In experimental studies of nine healthy volunteers, the spatial filters improved the signal-to-noise ratio of the MCG signals by about 500% on average. This spatial filtering method can be used for measurements of MCG signals in a magnetically noisy environment.     

独立分量分析的拟牛顿迭代算法及其在视觉诱发电位特征提取中的应用

少次叠加平均处理后的视觉诱发电位（VEP）中仍含有一定的背景噪声．对其进行进一步的提取与处理有重要的实用价值。独立分量分析（ICA）能够从混合信号中分离出最独立的成分，有效抑制噪声。本文尝试采用ICA的拟牛顿迭代算法进行VEP特征提取，介绍该方法的原理、实验和结果，并与采用牛顿迭代准则的快速独立孕量分析（Fast ICA）算法进行了比较。结果表明，基于拟牛顿法的ICA可以有效增强信号，从少次叠加平均的结果中提取出易于辨识的VEP的P300信号，具有较高的应用价值。     

An automated ECG-artifact removal method for trunk muscle surface EMG recordings

This study aimed at developing a method for automated electrocardiography (ECG) artifact detection and removal from trunk electromyography signals. Independent Component Analysis (ICA) method was applied to the simulated data set of ECG-corrupted surface electromyography (SEMG) signals. Independent Components (ICs) correspond to ECG artifact were then identified by an automated detection algorithm and subsequently removed. The detection performance of the algorithm was compared to that by visual inspection, while the artifact elimination performance was compared with Butterworth high pass filter at 30 Hz cutoff (BW HPF 30). The automated ECG-artifact detection algorithm successfully recognized the ECG source components in all data sets with a sensitivity of 100% and specificity of 99%. Better performance indicated by a significantly higher correlation coefficient (p < 0.001) with the original EMG recordings was found in the SEMG data cleaned by the ICA-based method, than that by BW HPF 30. The automated ECG-artifact removal method for trunk SEMG recordings proposed in this study was demonstrated to produce a very good detection rate and preserved essential EMG components while keeping its distortion to minimum. The automatic nature of our method has solved the problem of visual inspection by standard ICA methods and brings great clinical benefits.     

Impact of Spatial Filters During Sensor Selection in a Visual P300 Brain-Computer Interface

A challenge in designing a Brain-Computer Interface (BCI) is the choice of the channels, e.g. the most relevant sensors. Although a setup with many sensors can be more efficient for the detection of Event-Related Potential (ERP) like the P300, it is relevant to consider only a low number of sensors for a commercial or clinical BCI application. Indeed, a reduced number of sensors can naturally increase the user comfort by reducing the time required for the installation of the EEG (electroencephalogram) cap and can decrease the price of the device. In this study, the influence of spatial filtering during the process of sensor selection is addressed. Two of them maximize the Signal to Signal-plus-Noise Ratio (SSNR) for the different sensor subsets while the third one maximizes the differences between the averaged P300 waveform and the non P300 waveform. We show that the locations of the most relevant sensors subsets for the detection of the P300 are highly dependent on the use of spatial filtering. Applied on data from 20 healthy subjects, this study proves that subsets obtained where sensors are suppressed in relation to their individual SSNR are less efficient than when sensors are suppressed in relation to their contribution once the different selected sensors are combined for enhancing the signal. In other words, it highlights the difference between estimating the P300 projection on the scalp and evaluating the more efficient sensor subsets for a P300-BCI. Finally, this study explores the issue of channel commonality across subjects. The results support the conclusion that spatial filters during the sensor selection procedure allow selecting better sensors for a visual P300 Brain-Computer Interface.     

A hybrid method of application of independent component analysis to in vivo 1H MR spectra of childhood brain tumours

Independent component analysis (ICA) can automatically extract individual metabolite, macromolecular and lipid (MMLip) components from a series of in vivo MR spectra. The traditional feature extraction (FE)-based ICA approach is limited, in that a large sample size is required and a combination of metabolite and MMLip components can appear in the same independent component. The alternative ICA approach, based on blind source separation (BSS), is weak when dealing with overlapping peaks. Combining the advantages of both BSS and FE methods may lead to better results. Thus, we propose an ICA approach involving a hybrid of the BSS and FE techniques for the automated decomposition of a series of MR spectra. Experiments were performed on synthesised and patient in vivo childhood brain tumour MR spectra datasets. The hybrid ICA method showed an improvement in the decomposition ability compared with BSS-ICA or FE-ICA, with an increased correlation between the independent components and simulated metabolite and MMLip signals. Furthermore, we were able to automatically extract metabolites from the patient MR spectra dataset that were not in commonly used basis sets (e.g. guanidinoacetate).     

A method for detection of Alzheimer's disease using ICA-enhanced EEG measurements

OBJECTIVE: Many researchers have studied automatic EEG classification and recently a lot of work has been done on artefact-removal from EEG data using independent component analyses (ICA). However, demonstrating that a ICA-processed multichannel EEG measurement becomes more interpretable compared to the raw data (as is usually done in work on ICA-processing of EEG data) does not yet prove that detection of (incipient) anomalies is also better possible after ICA-processing. The objective of this study is to show that ICA-preprocessing is useful when constructing a detection system for Alzheimer's disease. METHODS AND MATERIAL: The paper describes a method for detection of EEG patterns indicative of Alzheimer's disease using automatic pattern recognition techniques. Our method incorporates an artefact removal stage based on ICA prior to automatic classification. The method is evaluated on measurements of a length of 8s from two groups of patients, where one group is in an initial stage of the disease (28 patients), whereas the other group is in a more progressed stage (15 patients). Both setups include a control group that should be classified as normal (10 and 21, respectively). RESULTS: Our final classification results for the group with severe Alzheimer's disease are comparable to the best results from literature. We show that ICA-based reduction of artefacts improves classification results for patients in an initial stage. CONCLUSION: We conclude that a more robust detection of Alzheimer's disease related EEG patterns may be obtained by employing ICA as ICA based pre-processing of EEG data can improve classification results for patients in an initial stage of Alzheimer's disease.     

两导心电信号独立分量分析算法的研究

根据独立分量分析(ICA)理论,要想在观测信号中提取出独立分量,观测信号的数目必须大于或等于独立分量的数目,因此要求采用ICA算法的胎儿心电图机导联数必须大于一定数目,但在实际应用中常常难以满足这个条件。故本文提出了一种基于少数导联心电(ECG)信号的胎儿心电(FECG)提取算法,结合FECG和自适应噪声抵消算法,从两导采集于孕妇腹部体表的ECG信号中提取FECG。实验表明,该方法能够获得清晰的FECG信号。     

基于扩展Infomax ICA的ERP少次提取方法研究

事件相关电位(event related potential,ERP)提取是脑电研究的重点之一,目前临床上主要通过相干平均的方法来获取.由于脑电的非平稳性,使其需要大量重复刺激才能获得,对于受试者极不方便,也不利于ERP的实时检测.本文以反映大脑稀少认知事件的相关电位P300为例,采用扩展Infomax(extended informationmaximization)独立分量分析(independent component analysis,ICA)算法,先滤除眼动、工频干扰,再重构脑电数据,最后经少次叠加即可得到与通常需多次相干平均结果相近的比较满意的P300波形.说明ICA算法在ERP的峰值和潜伏期模式识别上具有较为明显的效果,具有潜在的临床工程应用价值.     

Influence of task difficulty on the features of event-related potential during visual oddball task

We present a comprehensive analysis of the change in event-related potential (ERP) due to task difficulty during a visual oddball task. Specifically, we investigated the inter-subject difference in difficulty-related change of ERP patterns using single-trial ERP analysis focusing on P300 and P2 components. ERPs were recorded and analyzed from 14 subjects while performing a visual oddball task with two difficulty levels. After extracting independent components (ICs) from single-trial ERPs, the averaged ERPs were used to identify which ICs originated from major ERP components. The ERP components were estimated from single-trial waveforms by back-projecting relevant ICs onto scalp electrodes after removing all other ICs; thus, the comparison of ERP components could be performed for each subject. The averaged P300 amplitude was smaller and latency was larger for the more difficult task, and this tendency was also observed for single-trial ERP analysis within each subject. P2 amplitude increased for the hard task for both group and individual analyses, suggesting that the P2 may be interpreted as a manifestation of task relevance evaluation or response generation. The P2 amplitude and latency were more notably correlated with response time for the more difficult task.     

Automatic detection method of P300 waveform in the single sweep records by using a neural network

Event-related potentials (ERPs) are responses related to the recognition of certain stimuli. P300 is the most important positive component in the ERP and appears around 300 ms after the target stimulus in the oddball paradigm. In our previous work, we proposed a method for the automatic detection of the P300 waveform in single-sweep records by using a correlation technique. However, determination of the threshold values of the P300 waveform for the correlation study was not an easy task. In skirting this problem, we developed an automatic method of detecting a single-sweep P300 waveform by using an artificial neural network. We selected appropriate characteristic parameters of positive peaks as input signals for the input layer units, and the weights between the layers were determined by using the back-propagation algorithm. The neural network for P300 detection was obtained automatically, based on the data of ERPs obtained from 11 healthy males, and gave substantial accuracy for P300 detection. Furthermore, by using this neural network we clarified the way in which the P300 waveform is judged visually by each inspector.     

A method for the automatic reconstruction of fetal cardiac signals from magnetocardiographic recordings

Fetal magnetocardiography (fMCG) allows monitoring the fetal heart function through algorithms able to retrieve the fetal cardiac signal, but no standardized automatic model has become available so far. In this paper, we describe an automatic method that restores the fetal cardiac trace from fMCG recordings by means of a weighted summation of fetal components separated with independent component analysis (ICA) and identified through dedicated algorithms that analyse the frequency content and temporal structure of each source signal. Multichannel fMCG datasets of 66 healthy and 4 arrhythmic fetuses were used to validate the automatic method with respect to a classical procedure requiring the manual classification of fetal components by an expert investigator. ICA was run with input clusters of different dimensions to simulate various MCG systems. Detection rates, true negative and false positive component categorization, QRS amplitude, standard deviation and signal-to-noise ratio of reconstructed fetal signals, and real and per cent QRS differences between paired fetal traces retrieved automatically and manually were calculated to quantify the performances of the automatic method. Its robustness and reliability, particularly evident with the use of large input clusters, might increase the diagnostic role of fMCG during the prenatal period.     

Performance comparison of six independent components analysis algorithms for fetal signal extraction from real fMCG data

In this study we compare the performance of six independent components analysis (ICA) algorithms on 16 real fetal magnetocardiographic (fMCG) datasets for the application of extracting the fetal cardiac signal. We also compare the extraction results for real data with the results previously obtained for synthetic data. The six ICA algorithms are FastICA, CubICA, JADE, Infomax, MRMI-SIG and TDSEP. The results obtained using real fMCG data indicate that the FastICA method consistently outperforms the others in regard to separation quality and that the performance of an ICA method that uses temporal information suffers in the presence of noise. These two results confirm the previous results obtained using synthetic fMCG data. There were also two notable differences between the studies based on real and synthetic data. The differences are that all six ICA algorithms are independent of gestational age and sensor dimensionality for synthetic data, but depend on gestational age and sensor dimensionality for real data. It is possible to explain these differences by assuming that the number of point sources needed to completely explain the data is larger than the dimensionality used in the ICA extraction.     

Automatic correction of ocular artifacts in the EEG: a comparison of regression-based and component-based methods.

A variety of procedures have been proposed to correct ocular artifacts in the electroencephalogram (EEG), including methods based on regression, principal components analysis (PCA) and independent component analysis (ICA). The current study compared these three methods, and it evaluated a modified regression approach using Bayesian adaptive regression splines to filter the electrooculogram (EOG) before computing correction factors. We applied each artifact correction procedure to real and simulated EEG data of varying epoch lengths and then quantified the impact of correction on spectral parameters of the EEG. We found that the adaptive filter improved regression-based artifact correction. An automated PCA method effectively reduced ocular artifacts and resulted in minimal spectral distortion, whereas ICA correction appeared to distort power between 5 and 20 Hz. In general, reducing the epoch length improved the accuracy of estimating spectral power in the alpha (7.5-12.5 Hz) and beta (12.5-19.5 Hz) bands, but it worsened the accuracy for power in the theta (3.5-7.5 Hz) band and distorted time domain features. Results supported the use of regression-based and PCA-based ocular artifact correction and suggested a need for further studies examining possible spectral distortion from ICA-based correction procedures.     

ICA-based muscle–tendon units localization and activation analysis during dynamic motion tasks

This study proposed an independent component analysis (ICA)-based framework for localization and activation level analysis of muscle–tendon units (MTUs) within skeletal muscles during dynamic motion. The gastrocnemius muscle and extensor digitorum communis were selected as target muscles. High-density electrode arrays were used to record surface electromyographic (sEMG) data of the targeted muscles during dynamic motion tasks. First, the ICA algorithm was used to decompose multi-channel sEMG data into a weight coefficient matrix and a source matrix. Then, the source signal matrix was analyzed to determine EMG sources and noise sources. The weight coefficient vectors corresponding to the EMG sources were mapped to target muscles to find the location of the MTUs. Meanwhile, the activation level changes in MTUs during dynamic motion tasks were analyzed based on the corresponding EMG source signals. Eight subjects were recruited for this study, and the experimental results verified the feasibility and practicality of the proposed ICA-based method for the MTUs’ localization and activation level analysis during dynamic motion. This study provided a new, in-depth way to analyze the functional state of MTUs during dynamic tasks and laid a solid foundation for MTU-based accurate muscle force estimation, muscle fatigue prediction, neuromuscular control characteristic analysis, etc.