Quality and denoising in real‐time functional magnetic resonance imaging neurofeedback: A methods review

Neurofeedback training using real‐time functional magnetic resonance imaging (rtfMRI‐NF) allows subjects voluntary control of localised and distributed brain activity. It has sparked increased interest as a promising non‐invasive treatment option in neuropsychiatric and neurocognitive disorders, although its efficacy and clinical significance are yet to be determined. In this work, we present the first extensive review of acquisition, processing and quality control methods available to improve the quality of the neurofeedback signal. Furthermore, we investigate the state of denoising and quality control practices in 128 recently published rtfMRI‐NF studies. We found: (a) that less than a third of the studies reported implementing standard real‐time fMRI denoising steps, (b) significant room for improvement with regards to methods reporting and (c) the need for methodological studies quantifying and comparing the contribution of denoising steps to the neurofeedback signal quality. Advances in rtfMRI‐NF research depend on reproducibility of methods and results. Notably, a systematic effort is needed to build up evidence that disentangles the various mechanisms influencing neurofeedback effects. To this end, we recommend that future rtfMRI‐NF studies: (a) report implementation of a set of standard real‐time fMRI denoising steps according to a proposed COBIDAS‐style checklist ( https://osf.io/kjwhf/ ), (b) ensure the quality of the neurofeedback signal by calculating and reporting community‐informed quality metrics and applying offline control checks and (c) strive to adopt transparent principles in the form of methods and data sharing and support of open‐source rtfMRI‐NF software. Code and data for reproducibility, as well as an interactive environment to explore the study data, can be accessed at https://github.com/jsheunis/quality‐and‐denoising‐in‐rtfmri‐nf.     

Efficient Denoising Framework for Mammogram Images with a New Impulse Detector and Non-Local Means

Objective: The survival rates of breast cancer are increasing as screening and diagnosis improve. The removal of noise is revealed to be a significant step for automatic - computer aided detection (CAD) of microcalcification in digital mammography. Methods: In this paper, a combined approach for eradicating impulse noise from digital mammograms is proposed. The process is achieved in two stages, detection of noise followed by filtering of noise. The detection of noise is carried out by using Modified Robust Outlyingness Ratio (mROR) trailed by an extended NL (Non-Local)-means filter for filtering mechanism. Results: According to the value of mROR, all pixels in mammogram images are divided into four distinct groups. In each cluster, many decision rules are then applied for detecting the impulse noise. Filtering is done with NL-means filter by providing a reference mammogram image. Conclusion: The comparative analysis and evaluated results are compared with some existing filters which indicate that the proposed structure outperforms the analysed result of others.     

瞬态诱发耳声发射信号的小波阈值去噪

目的瞬态诱发耳声发射信号是从人的外耳检测到的微弱的音频能量,在测试过程中常混入各种随机噪声,本文尝试对瞬态诱发耳声发射信号进行去噪,以提高信号的信噪比,为进一步的临床应用(如频谱分析)奠定基础.方法小波变换阈值法.选用了sym8小波,软阈值处理方法,阈值选取规则为Minimax法.结果去噪后相关系数加大,信噪比提高.信噪比平均提高约10%.结论小波变换阈值法对TEOAE信号去噪取得了较好的效果.     

Approximation of the expected value of the harmonic mean and some applications

Although the harmonic mean (HM) is mentioned in textbooks along with the arithmetic mean (AM) and the geometric mean (GM) as three possible ways of summarizing the information in a set of observations, its appropriateness in some statistical applications is not mentioned in textbooks. During the last 10 y a number of papers were published giving some statistical applications where HM is appropriate and provides a better performance than AM. In the present paper some additional applications of HM are considered. The key result is to find a good approximation to E(H_n), the expectation of the harmonic mean of n observations from a probability distribution. In this paper a second-order approximation to E(H_n) is derived and applied to a number of problems.The harmonic mean H_n of n observations Z₁, …, Z_n drawn from a population is defined byHn=n∑i=1n1Zi.[1]There have been a number of applications of the harmonic mean in recent papers. A more general version of H_n with weights w₁, …, w_n isHn(w)=∑i=1nwi∑i=1nwiZi.[2]where w = (w₁,…,w_n)^T. The harmonic mean H_n is used to provide the average rate in physics and to measure the price ratio in finance as well as the program execution rate in computer engineering. Some statistical applications of the harmonic mean are given in refs. 1–4, among others. H_n(w) has been used in evaluation of the portfolio price-to-earnings ratio value (ref. 5, p. 339) and the signal-to-interference-and-noise ratio (6) among others. The asymptotic properties of H_n including the asymptotic expansion of E(H_n) are investigated in refs. 7 and 8 by either assuming that some moments of 1/Z_i are finite or that Z_i s follow the Poisson distribution. It is noted that recent papers (9, 10) enable one to use saddle-point approximation to give the asymptotic expansion of E(H_n) to any given order of 1/n for some constants c₀, c₁, c₂, …, i.e.,E(Hn)=c0+c1n+c2n2+⋯.[3]However, such methods are not applicable for obtaining the asymptotic expansion of H_n when the first moment of 1/Z_i is infinite. In ref. 3, Z_i s are assumed to follow a uniform distribution in the interval (0,1), i.e., U(0,1), motivated by learning theory. Using the property that the inverse of H_n converges to the stable law, ref. 3 showed thatE(Hn)∼1log(n),[4]where the symbol “∼” means asymptotic equivalence as n → ∞. Our interest in this paper is to determine the second term in the asymptotic expansion of E(H_n) or the general version E(H_n(w)) under more general assumptions on distributions of Z_i s. We show that under mild assumptions,E(Hn)∼1log(n){1+c1log(n)},[5]where the constant c₁ will be given. In addition, we use the approach for obtaining [5] to the case that the first moment of 1/Z_i is finite, motivated by evaluation of the marginal likelihood in ref. 11.     

基于小波奇异点检测和阈值去噪的眨眼伪迹去除方法

目的眨眼伪迹是脑电中一种常见且影响严重的伪迹。本论文提出一种基于小波奇异点检测和阈值去噪的眨眼伪迹去除方法,无需眼电参考信号,做到自动去除单导脑电信号中的眨眼伪迹。方法首先利用小波奇异点检测特性以检测眨眼伪迹的峰值位置,然后只对眨眼伪迹区域进行小波阈值去噪。结果实验结果表明,本方法能够有效检测眨眼伪迹,避免了普通方法去噪时对非眨眼区域的影响。结论本方法使用的阈值和阈值函数优于典型的阈值和软、硬阈值函数,有效地去除了脑电中的眨眼伪迹。     

Semi-supervised learning of the electronic health record for phenotype stratification

Patient interactions with health care providers result in entries to electronic health records (EHRs). EHRs were built for clinical and billing purposes but contain many data points about an individual. Mining these records provides opportunities to extract electronic phenotypes, which can be paired with genetic data to identify genes underlying common human diseases. This task remains challenging: high quality phenotyping is costly and requires physician review; many fields in the records are sparsely filled; and our definitions of diseases are continuing to improve over time. Here we develop and evaluate a semi-supervised learning method for EHR phenotype extraction using denoising autoencoders for phenotype stratification. By combining denoising autoencoders with random forests we find classification improvements across multiple simulation models and improved survival prediction in ALS clinical trial data. This is particularly evident in cases where only a small number of patients have high quality phenotypes, a common scenario in EHR-based research. Denoising autoencoders perform dimensionality reduction enabling visualization and clustering for the discovery of new subtypes of disease. This method represents a promising approach to clarify disease subtypes and improve genotype-phenotype association studies that leverage EHRs.     

Comparative study of wavelet denoising in myoelectric control applications

Here, the wavelet analysis has been investigated to improve the quality of myoelectric signal before use in prosthetic design. Effective Surface Electromyogram (SEMG) signals were estimated by first decomposing the obtained signal using wavelet transform and then analysing the decomposed coefficients by threshold methods. With the appropriate choice of wavelet, it is possible to reduce interference noise effectively in the SEMG signal. However, the most effective wavelet for SEMG denoising is chosen by calculating the root mean square value and signal power values. The combined results of root mean square value and signal power shows that wavelet db4 performs the best denoising among the wavelets. Furthermore, time domain and frequency domain methods were applied for SEMG signal analysis to investigate the effect of muscle-force contraction on the signal. It was found that, during sustained contractions, the mean frequency (MNF) and median frequency (MDF) increase as muscle force levels increase.     

联合主成分分析-小波与整体平均经验模态分解的锋电位去噪方法

多通道微电极阵列记录的锋电位(Spike)十分微弱,极易受干扰,其含噪的特性影响了Spike检出的准确率。针对Spike检测过程中通常存在的独立白噪声、相关噪声与有色噪声,本文结合主成分分析(PCA)、小波分析和自适应时频分析,提出PCA-小波(PCAW)与整体平均经验模态分解(EEMD)联合的去噪新方法(PCWE)。首先,利用PCA提取多通道神经信号通道间的主成分作为相关噪声去除;然后利用小波阈值法对独立白噪声进行去除;最后利用EEMD把噪声分解到各层本质模态函数中,对有色噪声进行去除。仿真结果表明,PCWE使信噪比约提高2.67 dB,标准差约减小0.4μV,显著提高了Spike的检出精确率;实测数据结果表明,PCWE能使信噪比约提高1.33 dB,标准差约减小18.33μV,表现出良好的去噪性能。本文研究结果表明,PCWE可以提高Spike信号的可靠性,或可为神经信号的编码解码提供一种新型有效的锋电位去噪方法。     

基于典型相关稀疏自编码器的精神分裂症的分类

通过结合大脑核磁共振成像和基因组信息进行全面系统的分析,影像遗传学已被广泛用于帮助诊断和治疗精神疾病（例如精神分裂症）。本文采用单核苷酸多态性数据和功能性磁共振成像数据联合分析,提出深度典型相关稀疏自编码器模型,探索两类数据之间的非线性关联并进行降维,对精神分裂症患者和健康对照进行分类。最后,实验结果表明,使用深度典型相关稀疏自编码器模型比其他传统模型具有更高的分类准确性。     

基于比率距离的自适应超声图像去噪方法

针对超声图像噪声的瑞利分布特性,使用一种新的自适应超声图像去噪方法,改进固定窗口包含边缘时无法做到沿边缘方向滤波的不足。采用可自由伸缩的自适应滤波窗口,首先针对瑞利分布的噪声引入比率距离,得到超声图像像素间的相似度距离,然后考虑像素的邻域图像块均值,解决相似度距离之间比较的问题,最后像素根据新的相似度距离进行八方向伸展,得到不规则形状的滤波窗口进行去噪。用仿真超声图像和临床超声图像进行实验,图像评价指标结果表明该算法优于经典算法,更适用于去除超声图像的斑点噪声,在去除噪声的同时能够较好地保留细节边缘。