Because of the long acquisition time and spin-echo planar imaging sequence, diffusion weight magnetic resonance image (DWI) should be denoised effectively to ensure the follow-up applications. The commonly used denoising methods which induced from gray level image lack the use of the specific information from multiple magnitude directions. This paper, therefore, proposes a modified linear minimum mean square error (LMMSE) denosing method used for DWI. The proposed method uses the local information to estimate the parameter of the Rician noise and modifies the LMMSE using the information of multiple magnitude directions synthetically. The simulation and experiment of the synthetic DWI and real human brain DWI dataset demonstrate that the proposed method can more effectively remove the Rician noise compared to the commonly used denoising method and improve the robustness and validity of the diffusion tensor magnetic resonance image (DTI).
Due to the characteristics and environmental factors, electrocardiogram (ECG) signals are usually interfered by noises in the course of signal acquisition, so it is crucial for ECG intelligent analysis to eliminate noises in ECG signals. On the basis of wavelet transform, threshold parameters were improved and a more appropriate threshold expression was proposed. The discrete wavelet coefficients were processed using the improved threshold parameters, the accurate wavelet coefficients without noises were gained through inverse discrete wavelet transform, and then more original signal coefficients could be preserved. MIT-BIH arrythmia database was used to validate the method. Simulation results showed that the improved method could achieve better denoising effect than the traditional ones.
Surface electromyogram (sEMG) may have low signal to noise ratios. An adaptive wavelet thresholding technique was developed in this study to remove noise contamination from sEMG signals. Compared with conventional wavelet thresholding methods, the adaptive approach can adjust thresholds based on different signal to noise ratios of the processed signal, thus effectively removing noise contamination and reducing distortion of the EMG signal. The advantage of the developed adaptive thresholding method was demonstrated using simulated and experimental sEMG recordings.
Fetal heart sound is nonlinear and non-stationary, which contains a lot of noise when it is colleced, so the denoising method is important. We proposed a new denoising method in our study. Firstly, we chose the preprocessing of low-pass filter with a cutoff frequency of 200 Hz and the re-sampling. Secondly, we decomposed the signal based on empirical mode decomposition method (EMD) of Hilbert-Huang transform, then denoised some selected target components with wavelet soft threshold adaptive noise cancellation algorithm. Finally we got the clean fetal heart sound by combining the target components. In the EMD, we used a mask signal to eliminate the mode mixing problem, used mirroring extension method to eliminate the end effect, and referenced the stopping rule from the research of Rilling. This method eliminated the baseline drift and noise at once. To compare with wavelet transform(WT), mathematical morphology (MM) and the Fourier transform (FT), the SNR was improved obviously, and the RMSE was the minimum, which could satisfy the need of the practical application.
Considering the survival rate of small animals and the continuity of the experiments, high-dose X-ray shooting process is not suitable for the small animals in computed tomography (CT) experiments. But the low-dose process results with images might be polluted by noises which are not conducive for the experiments. In order to solve this problem, we in this paper introduce a global dictionary learning based denoising method to apply the promotion of the low dose CT image. We at first adopted the K-means singular value decomposition (K-SVD) algorithm to train a global dictionary based on the high dose CT image. Then, the noise image could be decomposed into sparse component which was free from noise through the orthogonal matching pursuit (OMP) algorithm. Finally, the noise-free image could be achieved by reconstructing the image only with its sparse components. The experiments results showed that the method we proposed here could decrease the noise efficiently and remain the details, and it would help promote the low dose image quality and increase the survival rate of the small animals.
Electrocardiogram (ECG) is easily submerged in noise of the complex environment during remote medical treatment, and this affects the intelligent diagnosis of cardiovascular diseases. Considering this situation, this paper proposes an echo state network (ESN) denoising algorithm based on recursive least square (RLS) for ECG signals. The algorithm trains the ESN through the RLS method, and can automatically learn the deep nonlinear and differentiated characteristics in the noisy ECG data, and then the network can use these characteristic to separate out clear ECG signals automatically. In the experiment, the proposed method is compared with the wavelet transform with subband dependent threshold and the S-transform method by evaluating the signal-to-noise ratio and root mean square error. Experimental results show that the denoising accuracy is better and the low frequency component of the signal is well preserved. This method can effectively filter out complex noise and effectively preserve the effective information of ECG signals, which lays a foundation for the recognition of ECG signal feature waveform and the intelligent diagnosis of cardiovascular disease.
Spike recorded by multi-channel microelectrode array is very weak and susceptible to interference, whose noisy characteristic affects the accuracy of spike detection. Aiming at the independent white noise, correlation noise and colored noise in the process of spike detection, combining principal component analysis (PCA), wavelet analysis and adaptive time-frequency analysis, a new denoising method (PCWE) that combines PCA-wavelet (PCAW) and ensemble empirical mode decomposition is proposed. Firstly, the principal component was extracted and removed as correlation noise using PCA. Then the wavelet-threshold method was used to remove the independent white noise. Finally, EEMD was used to decompose the noise into the intrinsic modal function of each layer and remove the colored noise. The simulation results showed that PCWE can increase the signal-to-noise ratio by about 2.67 dB and decrease the standard deviation by about 0.4 μV, which apparently improved the accuracy of spike detection. The results of measured data showed that PCWE can increase the signal-to-noise ratio by about 1.33 dB and reduce the standard deviation by about 18.33 μV, which showed its good denoising performance. The results of this study suggests that PCWE can improve the reliability of spike signal and provide an accurate and effective spike denoising new method for the encoding and decoding of neural signal.
Denoising methods based on wavelet analysis and empirical mode decomposition cannot essentially track and eliminate noise, which usually cause distortion of heart sounds. Based on this problem, a heart sound denoising method based on improved minimum control recursive average and optimally modified log-spectral amplitude is proposed in this paper. The proposed method uses a short-time window to smoothly and dynamically track and estimate the minimum noise value. The noise estimation results are used to obtain the optimal spectrum gain function, and to minimize the noise by minimizing the difference between the clean heart sound and the estimated clean heart sound. In addition, combined with the subjective analysis of spectrum and the objective analysis of contribution to normal and abnormal heart sound classification system, we propose a more rigorous evaluation mechanism. The experimental results show that the proposed method effectively improves the time-frequency features, and obtains higher scores in the normal and abnormal heart sound classification systems. The proposed method can help medical workers to improve the accuracy of their diagnosis, and also has great reference value for the construction and application of computer-aided diagnosis system.
The automatic recognition technology of muscle fatigue has widespread application in the field of kinesiology and rehabilitation medicine. In this paper, we used surface electromyography (sEMG) to study the recognition of leg muscle fatigue during circuit resistance training. The purpose of this study was to solve the problem that the sEMG signals have a lot of noise interference and the recognition accuracy of the existing muscle fatigue recognition model is not high enough. First, we proposed an improved wavelet threshold function denoising algorithm to denoise the sEMG signal. Then, we build a muscle fatigue state recognition model based on long short-term memory (LSTM), and used the Holdout method to evaluate the performance of the model. Finally, the denoising effect of the improved wavelet threshold function denoising method proposed in this paper was compared with the denoising effect of the traditional wavelet threshold denoising method. We compared the performance of the proposed muscle fatigue recognition model with that of particle swarm optimization support vector machine (PSO-SVM) and convolutional neural network (CNN). The results showed that the new wavelet threshold function had better denoising performance than hard and soft threshold functions. The accuracy of LSTM network model in identifying muscle fatigue was 4.89% and 2.47% higher than that of PSO-SVM and CNN, respectively. The sEMG signal denoising method and muscle fatigue recognition model proposed in this paper have important implications for monitoring muscle fatigue during rehabilitation training and exercise.