Search

Bl factor is a key system parameter of the resonant blood viscoelastic sensor. In this paper, a dynamic measurement system for the spatial distribution of Bl factor based on velocity amplitude and motional impedance was designed. The system extracted the velocity amplitude and motional impedance of the coil under the dynamic condition of driving the sensor to generate simple harmonic oscillations using laser displacement and impedance analysis combined with in-phase/quadrature demodulation algorithm, and controlled the equilibrium position of the coil by adjusting the direct current component of the excitation current to realize the position scanning. In the position interval of [-240, 240] μm, the maximum coefficient of variation of the measurement results was 0.077 3%, and the maximum relative error to the simulation results was 2.937 9%, with a linear fitting correlation coefficient R 2 = 0.996 8. The system can be used to accurately measure the spatial distribution of Bl factor of the resonant blood viscoelastic sensor, which provides a technical support for the verification of the design of the sensor magnetic circuit.

Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.

Recently, deep learning has achieved impressive results in medical image tasks. However, this method usually requires large-scale annotated data, and medical images are expensive to annotate, so it is a challenge to learn efficiently from the limited annotated data. Currently, the two commonly used methods are transfer learning and self-supervised learning. However, these two methods have been little studied in multimodal medical images, so this study proposes a contrastive learning method for multimodal medical images. The method takes images of different modalities of the same patient as positive samples, which effectively increases the number of positive samples in the training process and helps the model to fully learn the similarities and differences of lesions on images of different modalities, thus improving the model's understanding of medical images and diagnostic accuracy. The commonly used data augmentation methods are not suitable for multimodal images, so this paper proposes a domain adaptive denormalization method to transform the source domain images with the help of statistical information of the target domain. In this study, the method is validated with two different multimodal medical image classification tasks: in the microvascular infiltration recognition task, the method achieves an accuracy of (74.79 ± 0.74)% and an F1 score of (78.37 ± 1.94)%, which are improved as compared with other conventional learning methods; for the brain tumor pathology grading task, the method also achieves significant improvements. The results show that the method achieves good results on multimodal medical images and can provide a reference solution for pre-training multimodal medical images.

As one of the standard electrophysiological signals in the human body, the photoplethysmography contains detailed information about the blood microcirculation and has been commonly used in various medical scenarios, where the accurate detection of the pulse waveform and quantification of its morphological characteristics are essential steps. In this paper, a modular pulse wave preprocessing and analysis system is developed based on the principles of design patterns. The system designs each part of the preprocessing and analysis process as independent functional modules to be compatible and reusable. In addition, the detection process of the pulse waveform is improved, and a new waveform detection algorithm composed of screening-checking-deciding is proposed. It is verified that the algorithm has a practical design for each module, high accuracy of waveform recognition and high anti-interference capability. The modular pulse wave preprocessing and analysis software system developed in this paper can meet the individual preprocessing requirements for various pulse wave application studies under different platforms. The proposed novel algorithm with high accuracy also provides a new idea for the pulse wave analysis process.

Medical image segmentation based on deep learning has become a powerful tool in the field of medical image processing. Due to the special nature of medical images, image segmentation algorithms based on deep learning face problems such as sample imbalance, edge blur, false positive, false negative, etc. In view of these problems, researchers mostly improve the network structure, but rarely improve from the unstructured aspect. The loss function is an important part of the segmentation method based on deep learning. The improvement of the loss function can improve the segmentation effect of the network from the root, and the loss function is independent of the network structure, which can be used in various network models and segmentation tasks in plug and play. Starting from the difficulties in medical image segmentation, this paper first introduces the loss function and improvement strategies to solve the problems of sample imbalance, edge blur, false positive and false negative. Then the difficulties encountered in the improvement of the current loss function are analyzed. Finally, the future research directions are prospected. This paper provides a reference for the reasonable selection, improvement or innovation of loss function, and guides the direction for the follow-up research of loss function.

The existing automatic sleep staging algorithms have the problems of too many model parameters and long training time, which in turn results in poor sleep staging efficiency. Using a single channel electroencephalogram (EEG) signal, this paper proposed an automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning (TL-SDResNet). Firstly, a total of 30 single-channel (Fpz-Cz) EEG signals from 16 individuals were selected, and after preserving the effective sleep segments, the raw EEG signals were pre-processed using Butterworth filter and continuous wavelet transform to obtain two-dimensional images containing its time-frequency joint features as the input data for the staging model. Then, a ResNet50 pre-trained model trained on a publicly available dataset, the sleep database extension stored in European data format (Sleep-EDFx) was constructed, using a stochastic depth strategy and modifying the output layer to optimize the model structure. Finally, transfer learning was applied to the human sleep process throughout the night. The algorithm in this paper achieved a model staging accuracy of 87.95% after conducting several experiments. Experiments show that TL-SDResNet50 can accomplish fast training of a small amount of EEG data, and the overall effect is better than other staging algorithms and classical algorithms in recent years, which has certain practical value.

When applying deep learning algorithms to magnetic resonance (MR) image segmentation, a large number of annotated images are required as data support. However, the specificity of MR images makes it difficult and costly to acquire large amounts of annotated image data. To reduce the dependence of MR image segmentation on a large amount of annotated data, this paper proposes a meta-learning U-shaped network (Meta-UNet) for few-shot MR image segmentation. Meta-UNet can use a small amount of annotated image data to complete the task of MR image segmentation and obtain good segmentation results. Meta-UNet improves U-Net by introducing dilated convolution, which can increase the receptive field of the model to improve the sensitivity to targets of different scales. We introduce the attention mechanism to improve the adaptability of the model to different scales. We introduce the meta-learning mechanism, and employ a composite loss function for well-supervised and effective bootstrapping of model training. We use the proposed Meta-UNet model to train on different segmentation tasks, and then use the trained model to evaluate on a new segmentation task, where the Meta-UNet model achieves high-precision segmentation of target images. Meta-UNet has a certain improvement in mean Dice similarity coefficient (DSC) compared with voxel morph network (VoxelMorph), data augmentation using learned transformations (DataAug) and label transfer network (LT-Net). Experiments show that the proposed method can effectively perform MR image segmentation using a small number of samples. It provides a reliable aid for clinical diagnosis and treatment.

Fetal electrocardiogram (ECG) signals provide important clinical information for early diagnosis and intervention of fetal abnormalities. In this paper, we propose a new method for fetal ECG signal extraction and analysis. Firstly, an improved fast independent component analysis method and singular value decomposition algorithm are combined to extract high-quality fetal ECG signals and solve the waveform missing problem. Secondly, a novel convolutional neural network model is applied to identify the QRS complex waves of fetal ECG signals and effectively solve the waveform overlap problem. Finally, high quality extraction of fetal ECG signals and intelligent recognition of fetal QRS complex waves are achieved. The method proposed in this paper was validated with the data from the PhysioNet computing in cardiology challenge 2013 database of the Complex Physiological Signals Research Resource Network. The results show that the average sensitivity and positive prediction values of the extraction algorithm are 98.21% and 99.52%, respectively, and the average sensitivity and positive prediction values of the QRS complex waves recognition algorithm are 94.14% and 95.80%, respectively, which are better than those of other research results. In conclusion, the algorithm and model proposed in this paper have some practical significance and may provide a theoretical basis for clinical medical decision making in the future.

The skin is the largest organ of the human body, and many visceral diseases will be directly reflected on the skin, so it is of great clinical significance to accurately segment the skin lesion images. To address the characteristics of complex color, blurred boundaries, and uneven scale information, a skin lesion image segmentation method based on dense atrous spatial pyramid pooling (DenseASPP) and attention mechanism is proposed. The method is based on the U-shaped network (U-Net). Firstly, a new encoder is redesigned to replace the ordinary convolutional stacking with a large number of residual connections, which can effectively retain key features even after expanding the network depth. Secondly, channel attention is fused with spatial attention, and residual connections are added so that the network can adaptively learn channel and spatial features of images. Finally, the DenseASPP module is introduced and redesigned to expand the perceptual field size and obtain multi-scale feature information. The algorithm proposed in this paper has obtained satisfactory results in the official public dataset of the International Skin Imaging Collaboration (ISIC 2016). The mean Intersection over Union (mIOU), sensitivity (SE), precision (PC), accuracy (ACC), and Dice coefficient (Dice) are 0.901 8, 0.945 9, 0.948 7, 0.968 1, 0.947 3, respectively. The experimental results demonstrate that the method in this paper can improve the segmentation effect of skin lesion images, and is expected to provide an auxiliary diagnosis for professional dermatologists.

Confocal laser endomicroscopy technology can obtain cell-level images in real time and in situ , which can assist doctors in real-time intraoperative diagnosis, but its non-invasiveness makes it difficult to relocate the optical biopsy site. The confocal probe localization algorithm can automatically calculate the coordinates of the probe tip, that is, the coordinates of the optical biopsy site. In this paper, a confocal probe localization algorithm based on region growing and endoscope size prior was proposed. The algorithm detected the probe region by region growing on the probe edge image, then searched for tip points based on a given probe axis, and iteratively optimized it. Finally, based on the single-degree-of-freedom motion characteristics of the probe, the three-dimensional coordinates of the tip of the probe were calculated by using the prior information of the size of the endoscope, which solved the scale uncertainty problem of the monocular camera. The confocal probe localization algorithm was tested on the dataset collected in this paper. The results showed that our algorithm no longer relied on the color information of the probe, avoided the influence of uneven illumination on the gray value of the probe pixels, and had a more robust location accuracy and running speed. Within the length of the probe extending out of the endoscope from 0 to 5 cm, the pixel error could be as low as 11.76 pixels, and the average relative position error could be as low as 1.66 mm, which can achieve the real-time and accurate localization of the confocal probe.

In deep learning-based image registration, the deformable region with complex anatomical structures is an important factor affecting the accuracy of network registration. However, it is difficult for existing methods to pay attention to complex anatomical regions of images. At the same time, the receptive field of the convolutional neural network is limited by the size of its convolution kernel, and it is difficult to learn the relationship between the voxels with far spatial location, making it difficult to deal with the large region deformation problem. Aiming at the above two problems, this paper proposes a cascaded multi-level registration network model based on transformer, and equipped it with a difficult deformable region perceptron based on mean square error. The difficult deformation perceptron uses sliding window and floating window techniques to retrieve the registered images, obtain the difficult deformation coefficient of each voxel, and identify the regions with the worst registration effect. In this study, the cascaded multi-level registration network model adopts the difficult deformation perceptron for hierarchical connection, and the self-attention mechanism is used to extract global features in the basic registration network to optimize the registration results of different scales. The experimental results show that the method proposed in this paper can perform progressive registration of complex deformation regions, thereby optimizing the registration results of brain medical images, which has a good auxiliary effect on the clinical diagnosis of doctors.

In recent years, exploring the physiological and pathological mechanisms of brain functional integration from the neural network level has become one of the focuses of neuroscience research. Due to the non-stationary and nonlinear characteristics of neural signals, its linear characteristics are not sufficient to fully explain the potential neurophysiological activity mechanism in the implementation of complex brain functions. In order to overcome the limitation that the linear algorithm cannot effectively analyze the nonlinear characteristics of signals, researchers proposed the transfer entropy (TE) algorithm. In recent years, with the introduction of the concept of brain functional network, TE has been continuously optimized as a powerful tool for nonlinear time series multivariate analysis. This paper first introduces the principle of TE algorithm and the research progress of related improved algorithms, discusses and compares their respective characteristics, and then summarizes the application of TE algorithm in the field of electrophysiological signal analysis. Finally, combined with the research progress in recent years, the existing problems of TE are discussed, and the future development direction is prospected.

The count and recognition of white blood cells in blood smear images play an important role in the diagnosis of blood diseases including leukemia. Traditional manual test results are easily disturbed by many factors. It is necessary to develop an automatic leukocyte analysis system to provide doctors with auxiliary diagnosis, and blood leukocyte segmentation is the basis of automatic analysis. In this paper, we improved the U-Net model and proposed a segmentation algorithm of leukocyte image based on dual path and atrous spatial pyramid pooling. Firstly, the dual path network was introduced into the feature encoder to extract multi-scale leukocyte features, and the atrous spatial pyramid pooling was used to enhance the feature extraction ability of the network. Then the feature decoder composed of convolution and deconvolution was used to restore the segmented target to the original image size to realize the pixel level segmentation of blood leukocytes. Finally, qualitative and quantitative experiments were carried out on three leukocyte data sets to verify the effectiveness of the algorithm. The results showed that compared with other representative algorithms, the proposed blood leukocyte segmentation algorithm had better segmentation results, and the mIoU value could reach more than 0.97. It is hoped that the method could be conducive to the automatic auxiliary diagnosis of blood diseases in the future.

The research shows that personality assessment can be achieved by regression model based on electroencephalogram (EEG). Most of existing researches use event-related potential or power spectral density for personality assessment, which can only represent the brain information of a single region. But some research shows that human cognition is more dependent on the interaction of brain regions. In addition, due to the distribution difference of EEG features among subjects, the trained regression model can not get accurate results of cross subject personality assessment. In order to solve the problem, this research proposes a personality assessment method based on EEG functional connectivity and domain adaption. This research collected EEG data from 45 normal people under different emotional pictures (positive, negative and neutral). Firstly, the coherence of 59 channels in 5 frequency bands was taken as the original feature set. Then the feature-based domain adaptation was used to map the feature to a new feature space. It can reduce the distribution difference between training and test set in the new feature space, so as to reduce the distribution difference between subjects. Finally, the support vector regression model was trained and tested based on the transformed feature set by leave-one-out cross-validation. What's more, this paper compared the methods used in previous researches. The results showed that the method proposed in this paper improved the performance of regression model and obtained better personality assessment results. This research provides a new method for personality assessment.

Aiming at the problems of individual differences in the asynchrony process of human lower limbs and random changes in stride during walking, this paper proposes a method for gait recognition and prediction using motion posture signals. The research adopts an optimized gated recurrent unit (GRU) network algorithm based on immune particle swarm optimization (IPSO) to establish a network model that takes human body posture change data as the input, and the posture change data and accuracy of the next stage as the output, to realize the prediction of human body posture changes. This paper first clearly outlines the process of IPSO's optimization of the GRU algorithm. It collects human body posture change data of multiple subjects performing flat-land walking, squatting, and sitting leg flexion and extension movements. Then, through comparative analysis of IPSO optimized recurrent neural network (RNN), long short-term memory (LSTM) network, GRU network classification and prediction, the effectiveness of the built model is verified. The test results show that the optimized algorithm can better predict the changes in human posture. Among them, the root mean square error (RMSE) of flat-land walking and squatting can reach the accuracy of 10 -3 , and the RMSE of sitting leg flexion and extension can reach the accuracy of 10 -2 . The R 2 value of various actions can reach above 0.966. The above research results show that the optimized algorithm can be applied to realize human gait movement evaluation and gait trend prediction in rehabilitation treatment, as well as in the design of artificial limbs and lower limb rehabilitation equipment, which provide a reference for future research to improve patients' limb function, activity level, and life independence ability.

In order to suppress the geometrical artifacts caused by random jitter in ray source scanning, and to achieve flexible ray source scanning trajectory and meet the requirements of task-driven scanning imaging, a method of free trajectory cone-beam computed tomography (CBCT) reconstruction is proposed in this paper. This method proposed a geometric calibration method of two-dimensional plane. Based on this method, the geometric calibration phantom and the imaging object could be simultaneously imaged. Then, the geometric parameters could be obtained by online calibration method, and then combined with the geometric parameters, the alternating direction multiplier method (ADMM) was used for image iterative reconstruction. Experimental results showed that this method obtained high quality reconstruction image with high contrast and clear feature edge. The root mean square errors (RMSE) of the simulation results were rather small, and the structural similarity (SSIM) values were all above 0.99. The experimental results showed that it had lower image information entropy (IE) and higher contrast noise ratio (CNR). This method provides some practical value for CBCT to realize trajectory freedom and obtain high quality reconstructed image.

The inverse problem of diffuse optical tomography (DOT) is ill-posed. Traditional method cannot achieve high imaging accuracy and the calculation process is time-consuming, which restricts the clinical application of DOT. Therefore, a method based on stacked auto-encoder (SAE) was proposed and used for the DOT inverse problem. Firstly, a traditional SAE method is used to solved the inverse problem. Then, the output structure of SAE neural network is improved to a single output SAE, which reduce the burden on the neural network. Finally, the improved SAE method is used to compare with traditional SAE method and traditional levenberg-marquardt (LM) iterative method. The result shows that the average time to solve the inverse problem of the method proposed in this paper is only 1.67% of the LM method. The mean square error (MSE) value is 46.21% lower than the traditional iterative method, 61.53% lower than the traditional SAE method, and the image correlation coefficient(ICC) value is 4.03% higher than the traditional iterative method, 18.7% higher than the traditional SAE method and has good noise immunity under 3% noise conditions. The research results in this article prove that the improved SAE method has higher image quality and noise resistance than the traditional SAE method, and at the same time has a faster calculation speed than the traditional iterative method, which is conducive to the application of neural networks in DOT inverse problem calculation.

Affective brain-computer interfaces (aBCIs) has important application value in the field of human-computer interaction. Electroencephalogram (EEG) has been widely concerned in the field of emotion recognition due to its advantages in time resolution, reliability and accuracy. However, the non-stationary characteristics and individual differences of EEG limit the generalization of emotion recognition model in different time and different subjects. In this paper, in order to realize the recognition of emotional states across different subjects and sessions, we proposed a new domain adaptation method, the maximum classifier difference for domain adversarial neural networks (MCD_DA). By establishing a neural network emotion recognition model, the shallow feature extractor was used to resist the domain classifier and the emotion classifier, respectively, so that the feature extractor could produce domain invariant expression, and train the decision boundary of classifier learning task specificity while realizing approximate joint distribution adaptation. The experimental results showed that the average classification accuracy of this method was 88.33% compared with 58.23% of the traditional general classifier. It improves the generalization ability of emotion brain-computer interface in practical application, and provides a new method for aBCIs to be used in practice.

Vision is an important way for human beings to interact with the outside world and obtain information. In order to research human visual behavior under different conditions, this paper uses a Gaussian mixture-hidden Markov model (GMM-HMM) to model the scanpath, and proposes a new model optimization method, time-shifting segmentation (TSS). The TSS method can highlight the characteristics of the time dimension in the scanpath, improve the pattern recognition results, and enhance the stability of the model. In this paper, a linear discriminant analysis (LDA) method is used for multi-dimensional feature pattern recognition to evaluates the rationality and the accuracy of the proposed model. Four sets of comparative trials were carried out for the model evaluation. The first group applied the GMM-HMM to model the scanpath, and the average accuracy of the classification could reach 0.507, which is greater than the opportunity probability of three classification (0.333). The second set of trial applied TSS method, and the mean accuracy of classification was raised to 0.610. The third group combined GMM-HMM with TSS method, and the mean accuracy of classification reached 0.602, which was more stable than the second model. Finally, comparing the model analysis results with the saccade amplitude (SA) characteristics analysis results, the modeling analysis method is much better than the basic information analysis method. Via analyzing the characteristics of three types of tasks, the results show that the free viewing task have higher specificity value and a higher sensitivity to the cued object search task. In summary, the application of GMM-HMM model has a good performance in scanpath pattern recognition, and the introduction of TSS method can enhance the difference of scanpath characteristics. Especially for the recognition of the scanpath of search-type tasks, the model has better advantages. And it also provides a new solution for a single state eye movement sequence.

The construction of brain functional network based on resting-state functional magnetic resonance imaging (fMRI) is an effective method to reveal the mechanism of human brain operation, but the common brain functional network generally contains a lot of noise, which leads to wrong analysis results. In this paper, the least absolute shrinkage and selection operator (LASSO) model in compressed sensing is used to reconstruct the brain functional network. This model uses the sparsity of L 1 -norm penalty term to avoid over fitting problem. Then, it is solved by the fast iterative shrinkage-thresholding algorithm (FISTA), which updates the variables through a shrinkage threshold operation in each iteration to converge to the global optimal solution. The experimental results show that compared with other methods, this method can improve the accuracy of noise reduction and reconstruction of brain functional network to more than 98%, effectively suppress the noise, and help to better explore the function of human brain in noisy environment.

With the rapid improvement of the perception and computing capacity of mobile devices such as smart phones, human activity recognition using mobile devices as the carrier has been a new research hot-spot. The inertial information collected by the acceleration sensor in the smart mobile device is used for human activity recognition. Compared with the common computer vision recognition, it has the following advantages: convenience, low cost, and better reflection of the essence of human motion. Based on the WISDM data set collected by smart phones, the inertial navigation information and the deep learning algorithm-convolutional neural network (CNN) were adopted to build a human activity recognition model in this paper. The K nearest neighbor algorithm (KNN) and the random forest algorithm were compared with the CNN network in the recognition accuracy to evaluate the performance of the CNN network. The classification accuracy of CNN model reached 92.73%, which was much higher than KNN and random forest. Experimental results show that the CNN algorithm model can achieve more accurate human activity recognition and has broad application prospects in predicting and promoting human health.

In order to solve the saturation distortion phenomenon of R component in fingertip video image, this paper proposes an iterative threshold segmentation algorithm, which adaptively generates the region to be detected for the R component, and extracts the human pulse signal by calculating the gray mean value of the region to be detected. The original pulse signal has baseline drift and high frequency noise. Combining with the characteristics of pulse signal, a zero phase digital filter is designed to filter out noise interference. Fingertip video images are collected on different smartphones, and the region to be detected is extracted by the algorithm proposed in this paper. Considering that the fingertip's pressure will be different during each measurement, this paper makes a comparative analysis of pulse signals extracted under different pressures. In order to verify the accuracy of the algorithm proposed in this paper in heart rate detection, a comparative experiment of heart rate detection was conducted. The results show that the algorithm proposed in this paper can accurately extract human heart rate information and has certain portability, which provides certain theoretical help for further development of physiological monitoring application on smartphone platform.

In order to eliminate the influence of motion artifacts, high-frequency noise and baseline drift on photoplethysmographic (PPG), and to obtain the accurate value of heart rate in motion state, this paper proposed a de-noising method of PPG signal based on normalized least mean square (NLMS) adaptive filtering combining ensemble empirical mode decomposition(EEMD). Firstly, the PPG signal containing noise is passed through an adaptive filter with a 3-axis acceleration sensor as a reference signal to filter out motion artifacts. Secondly, the PPG signal is decomposed by EEMD to obtain a series of intrinsic modal function (IMF) according to the frequency from high to low. The threshold range of the signal is judged by the permutation entropy (PE) criterion, thereby filtering out the high frequency noise and the baseline drift. The experimental results show that the Pearson correlation coefficient between the calculated heart rate of PPG signal and the standard heart rate based on electrocardiogram (ECG) signal is 0.731 and the average absolute error percentage is 6.10% under different motion states, which indicates that the method can accurately calculate the heart rate in moving state and is beneficial to the physiological monitoring under the state of human motion.

With the change of medical diagnosis and treatment mode, the quality of medical image directly affects the diagnosis and treatment of the disease for doctors. Therefore, realization of intelligent image quality control by computer will have a greater auxiliary effect on the radiographer's filming work. In this paper, the research methods and applications of image segmentation model and image classification model in the field of deep learning and traditional image processing algorithm applied to medical image quality evaluation are described. The results demonstrate that deep learning algorithm is more accurate and efficient than the traditional image processing algorithm in the effective training of medical image big data, which explains the broad application prospect of deep learning in the medical field. This paper developed a set of intelligent quality control system for auxiliary filming, and successfully applied it to the Radiology Department of West China Hospital and other city and county hospitals, which effectively verified the feasibility and stability of the quality control system.

To assess the background field removal method usually used in quantitative susceptibility mapping (QSM), and to analyze the cause of serious artifacts generated in the truncated k -space division (TKD) method, this paper discusses a variety of background field removal methods and proposes an improved method to suppress the artifacts of susceptibility inversion. Firstly, we scanned phase images with the gradient echo sequence and then compared the quality and the speed of reconstructed images of sophisticated harmonic artifact reduction for phase data (SHARP), regularization enable of SHARP (RESHARP) and laplacian boundary value (LBV) methods. Secondly, we analyzed the reasons for reconstruction artifacts caused by the multiple truncations and discontinuity of the TKD method, and an improved TKD method was proposed by increasing threshold truncation range and improving data continuity. Finally, the result of susceptibility inversion from the improved and original TKD method was compared. The results show that the reconstruction of SHARP and RESHARP are very fast, but SHARP reconstruction artifacts are serious and the reconstruction precision is not high and implementation of RESHARP is complicated. The reconstruction speed of LBV method is slow, but the detail of the reconstructed image is prominent and the precision is high. In the QSM inversion methods, the reconstruction artifact of the original TKD method is serious, while the improved method obtains good artifact suppression image and good inversion result of artifact regions.

Brain-computer interface (BCI) provides a direct communicating and controlling approach between the brain and surrounding environment, which attracts a wide range of interest in the fields of brain science and artificial intelligence. It is a core to decode the electroencephalogram (EEG) feature in the BCI system. The decoding efficiency highly depends on the feature extraction and feature classification algorithms. In this paper, we first introduce the commonly-used EEG features in the BCI system. Then we introduce the basic classical algorithms and their advanced versions used in the BCI system. Finally, we present some new BCI algorithms proposed in recent years. We hope this paper can spark fresh thinking for the research and development of high-performance BCI system.

Acute respiratory distress syndrome (ARDS) is a serious threat to human life and health disease, with acute onset and high mortality. The current diagnosis of the disease depends on blood gas analysis results, while calculating the oxygenation index. However, blood gas analysis is an invasive operation, and can't continuously monitor the development of the disease. In response to the above problems, in this study, we proposed a new algorithm for identifying the severity of ARDS disease. Based on a variety of non-invasive physiological parameters of patients, combined with feature selection techniques, this paper sorts the importance of various physiological parameters. The cross-validation technique was used to evaluate the identification performance. The classification results of four supervised learning algorithms using neural network, logistic regression, AdaBoost and Bagging were compared under different feature subsets. The optimal feature subset and classification algorithm are comprehensively selected by the sensitivity, specificity, accuracy and area under curve (AUC) of different algorithms under different feature subsets. We use four supervised learning algorithms to distinguish the severity of ARDS (P/F ≤ 300). The performance of the algorithm is evaluated according to AUC. When AdaBoost uses 20 features, AUC = 0.832 1, the accuracy is 74.82%, and the optimal AUC is obtained. The performance of the algorithm is evaluated according to the number of features. When using 2 features, Bagging has AUC = 0.819 4 and the accuracy is 73.01%. Compared with traditional methods, this method has the advantage of continuously monitoring the development of patients with ARDS and providing medical staff with auxiliary diagnosis suggestions.

The convective polymerase chain reaction (CCPCR) uses the principle of thermal convection to allow the reagent to flow in the test tube and achieve the purpose of amplification by the temperature difference between the upper and lower portions of the test tube. In order to detect the amplification effect in real time, we added a fluorophore to the reagent system to reflect the amplification in real time through the intensity of fluorescence. The experimental results show that the fluorescence curve conforms to the S-type trend of the amplification curve, but there is a certain jitter condition due to the instability of the thermal convection, which is not conducive to the calculation of the cycle threshold (CT value). In order to solve this problem, this paper uses the dynamic method, using the double S-type function model to fit the curve, so that the fluorescence curve is smooth and the initial concentration of the nucleic acid can be deduced better to achieve the quantitative purpose based on the curve. At the same time, the PSO+ algorithm is used to solve the double s-type function parameters, that is, particle swarm optimization (PSO) algorithm combined with Levenberg-Marquardt, Newton-CG and other algorithms for curve fitting. The proposed method effectively overcoms PSO randomness and the shortcoming of traditional algorithms such as Levenberg-Marquardt and Newton-CG which are easy to fall into the local optimal solution. The R 2 of the data fitting result can reach 0.999 8. This study is of guiding significance for the future quantitative detection of real-time fluorescent heat convection amplification.

To locate the nuclei in hematoxylin-eosin (HE) stained section images more simply, efficiently and accurately, a new method based on distance estimation is proposed in this paper, which shows a new mind on locating the nuclei from a clump image. Different from the mainstream methods, proposed method avoids the operations of searching the combined singles. It can directly locate the nuclei in a full image. Furthermore, when the distance estimation built on the matrix sequence of distance rough estimating (MSDRE) is combined with the fact that a center of a convex region must have the farthest distance to the boundary, it can fix the positions of nuclei quickly and precisely. In addition, a high accuracy and efficiency are achieved by this method in experiments, with the precision of 95.26% and efficiency of 1.54 second per thousand nuclei, which are better than the mainstream methods in recognizing nucleus clump samples. Proposed method increases the efficiency of nuclear location while maintaining the location's accuracy. This can be helpful for the automatic analysis system of HE images by improving the real-time performance and promoting the application of related researches.

Dual-energy computed tomography (CT) reconstruction imaging technology is an important development direction in the field of CT imaging. The mainstream model of dual-energy CT reconstruction algorithm is the basis material decomposition model, and the projection decomposition is the crucial technique. The projection decomposition algorithm based on projection matching was a general method. With establishing the energy spectrum lookup table, we can obtain the stable solution by the least squares matching method. But the computation cost will increase dramatically when size of lookup table enlarges and it will slow down the computer. In this paper, an acceleration algorithm based on projection matching is proposed. The proposed algorithm makes use of linear equations and plane equations to fit the lookup table data, so that the projection value of the decomposition coefficients can be calculated quickly. As the result of simulation experiment, the acceleration algorithm can greatly shorten the running time of the program to get the stable and correct solution.

The inverse problem of electrical impedance tomography (EIT) is seriously ill-posed, which restricts the clinical application of EIT. Regularization is an important numerical method to improve the stability of the EIT inverse problem as well as the resolution of the imaging. This paper proposes a self-diagnosis regularization method based on Tikhonov regularization and diagonal weight regularization method (DWRM). Firstly, the ill-posedness of the inverse problem is analyzed by sensitivity. Then, the performance of the self-diagnosis regularization is analyzed through the singular value theory. Finally, some simulated experiments including simulations and flume experiment are carried out and verify that the self-diagnosis regularization has better image quality and anti-noise ability than those of traditional regularization methods. The self-diagnosis regularization method weakens the ill-posedness of inverse problem of EIT and can prompt the practical application of EIT.

The automatic classification of epileptic electroencephalogram(EEG)is significant in the diagnosis and therapy of epilepsy.A classification algorithm for epileptic EEG based on wavelet multiscale analysis and extreme learning machine(ELM)is proposed in this paper.Firstly,wavelet multiscale analysis is applied to the original EEG to extract its sub-bands.Then,two nonlinear methods,i.e.Hurst exponent(Hurst)and sample entropy(SamEn)are used to the feature extraction of EEG and its sub-bands.Finally,ELM algorithm is employed in epileptic EEG classification with the nonlinear features.The proposed method in this paper achieved 99.5% classification accuracy for the discrimination between epileptic ictal and interictal EEG.The result implies that this method has good prospects in the diagnosis and therapy of epilepsy.

Sleep stage scoring is a hotspot in the field of medicine and neuroscience.Visual inspection of sleep is laborious and the results may be subjective to different clinicians.Automatic sleep stage classification algorithm can be used to reduce the manual workload.However,there are still limitations when it encounters complicated and changeable clinical cases.The purpose of this paper is to develop an automatic sleep staging algorithm based on the characteristics of actual sleep data.In the proposed improved K-means clustering algorithm,points were selected as the initial centers by using a concept of density to avoid the randomness of the original K-means algorithm.Meanwhile,the cluster centers were updated according to the‘Three-Sigma Rule’during the iteration to abate the influence of the outliers.The proposed method was tested and analyzed on the overnight sleep data of the healthy persons and patients with sleep disorders after continuous positive airway pressure(CPAP)treatment.The automatic sleep stage classification results were compared with the visual inspection by qualified clinicians and the averaged accuracy reached 76%.With the analysis of morphological diversity of sleep data,it was proved that the proposed improved K-means algorithm was feasible and valid for clinical practice.

Artifacts produced by chest compression during cardiopulmonary resuscitation(CPR)seriously affect the reliability of shockable rhythm detection algorithms.In this paper,we proposed an adaptive CPR artifacts elimination algorithm without needing any reference channels.The clean electrocardiogram(ECG)signals can be extracted from the corrupted ECG signals by incorporating empirical mode decomposition(EMD)and independent component analysis(ICA).For evaluating the performance of the proposed algorithm,a back propagation neural network was constructed to implement the shockable rhythm detection.A total of 1 484 corrupted ECG samples collected from pigs were included in the analysis.The results of the experiments indicated that this method would greatly reduce the effects of the CPR artifacts and thereby increase the accuracy of the shockable rhythm detection algorithm.

With the increasing number of electrocardiogram(ECG)data,extensive application requirements of computer-aided ECG analysis have occurred.In the paper,we propose a variety of strategies to improve the performance of clinical ECG classification algorithm based on Lead Convolutional Neural Network(LCNN).Firstly,we obtained two classifiers by using different preprocessing methods and training methods in the study.Then,we applied the multiple output prediction method to both of them independently.Finally,the Bayesian approach was employed to fuse them.Tests conducted using more than 150 000 ECG records showed that the proposed method had an accuracy of 85.04% and the area under receiver operating characteristic curve(AUC)was 0.918 5,which significantly outperforms traditional methods based on feature extraction techniques.

The nondestructive reconstruction of three-dimensional(3D)temperature field in biological tissue is always an important problem to be resolved in biomedical engineering field.This paper presents a novel method of nondestructive reconstruction of 3Dtemperature field in biological tissue based on multi-island genetic algorithm(MIGA).By this method,the resolving of inverse problem of bio-heat transfer is transformed to be a solving process of direct problem.An experiment and its corresponding simulation were carried out to verify the feasibility and reliability.In the experiment a high purity polypropylene material,whose thermophysical parameters were similar to the fat tissue being tested,were adopted so that it could avoid the negative results created by the other factors.We set the position P(x,y,z)as the point heat source in the biological tissue and its temperature t as optimization variable,got the experimental temperature values of the points in a module surface,subtracted them from the corresponding simulating temperature values in the same module surface,and then took the sum of absolute value.We took it as the objective function of successive iteration.It was found that the less the target value was,the more optimal the current variables,i.e.the heat source position and the temperature values,were.To improve the optimization efficiency,a novel establishment method of objective function was also provided.The simulating position and experimental position of heat source were very approximate to each other.When the optimum values are determined,the corresponding 3D temperature field is also confirmed,and the temperature distribution of arbitrary section can be acquired.The MIGA can be well applied in the reconstruction of 3Dtemperature field in biological tissue.Because of the differences between the MIGA and the traditional numerical methods,we do not have to acquire all the data of surface.It is convenient and fast,and shows a prosperous application future.

This paper presents a kind of automatic segmentation method for white blood cell based on HSI corrected space information fusion.Firstly,the original cell image is transformed to HSI colour space conversion.Because the transformation formulas of H component piecewise function was discontinuous,the uniformity of uniform visual cytoplasm area in the original image was lead to become lower in this channel.We then modified formulas,and then fetched information of nucleus,cytoplasm,red blood cells and background region according to distribution characteristics of the H,S and I-channel,using the theory and method of information fusion to build fusion imageⅠand fusion imageⅡ,which only contained cytoplasm and a small amount of interference,and fetched nucleus and cytoplasm respectively.Finally,we marked the nucleus and cytoplasm region and obtained the final result of segmentation.The simulation results showed that the new algorithm of image segmentation for white blood cell had high accuracy,robustness and universality.

This paper proposes a method based on quaternion for characterization a helix of proteins. The method defines the parameter called Quaternion Helix Axis Spherical Distance (QHASD) on the basis of mapping protein Cα frames' helical axis onto a unit sphere, and uses QHASD to characterize the a helix of the protein secondary structure. Application of this method has been verified based on the PDBselect database, with an a helix characterization accuracy of 91.7%. This method possesses significant advantages of high detection accuracy, low computation and clear geometric significance.

Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.

In order to monitor the emotional state changes of audience on real-time and to adjust the music playlist, we proposed an algorithm framework of an electroencephalogram (EEG) driven personalized affective music recommendation system based on the portable dry electrode shown in this paper. We also further finished a preliminary implementation on the Android platform. We used a two-dimensional emotional model of arousal and valence as the reference, and mapped the EEG data and the corresponding seed songs to the emotional coordinate quadrant in order to establish the matching relationship. Then, Mel frequency cepstrum coefficients were applied to evaluate the similarity between the seed songs and the songs in music library. In the end, during the music playing state, we used the EEG data to identify the audience's emotional state, and played and adjusted the corresponding song playlist based on the established matching relationship.

Electrocardiogram (ECG) signals are susceptible to be disturbed by 50 Hz power line interference (PLI) in the process of acquisition and conversion. This paper, therefore, proposes a novel PLI removal algorithm based on morphological component analysis (MCA) and ensemble empirical mode decomposition (EEMD). Firstly, according to the morphological differences in ECG waveform characteristics, the noisy ECG signal was decomposed into the mutated component, the smooth component and the residual component by MCA. Secondly, intrinsic mode functions (IMF) of PLI was filtered. The noise suppression rate (NSR) and the signal distortion ratio (SDR) were used to evaluate the effect of de-noising algorithm. Finally, the ECG signals were re-constructed. Based on the experimental comparison, it was concluded that the proposed algorithm had better filtering functions than the improved Levkov algorithm, because it could not only effectively filter the PLI, but also have smaller SDR value.

Six kinds of erythemato-squamous diseases have been common skin diseases, but the diagnosis of them has always been a problem. The quantitative data processing method is not suitable for erythemato-squamous data because they are categorical qualitative data. This paper proposed a new method based on group lasso penalized classification for the feature selection and classification for erythemato-squamous data with categorical qualitative data. The first categorical data of 33 dimensions were changed by the virtual code, and then 34th dimension age data were discretized and changed by the virtual code. Then the encoded data were grouped according to class group and variable group. Lastly Group Lasso penalized classification was executed. The classified accuracy of 10-fold cross validation was 98.88% ± 0.002 3%. Compared with those of other method in the literature, this new method is simpler, and better for effect and efficiency, and has stronger interpretability and stronger stability.

In this paper, an improved empirical mode decomposition (EMD) algorithm for phonocardiogram (PCG) signal de-noising is proposed. Based on PCG signal processing theory, the S1/S2 components can be extracted by combining the improved EMD-Wavelet algorithm and Shannon energy envelope algorithm. Firstly, by applying EMD-Wavelet algorithm for pre-processing, the PCG signal was well filtered. Then, the filtered PCG signal was saved and applied in the following processing steps. Secondly, time domain features, frequency domain features and energy envelope of the each intrinsic mode function's (IMF) were computed. Based on the time frequency domain features of PCG's IMF components which were extracted from the EMD algorithm and energy envelope of the PCG, the S1/S2 components were pinpointed accurately. Meanwhile, a detecting fixed method, which was based on the time domain processing, was proposed to amend the detection results. Finally, to test the performance of the algorithm proposed in this paper, a series of experiments was contrived. The experiments with thirty samples were tested for validating the effectiveness of the new method. Results of test experiments revealed that the accuracy for recognizing S1/S2 components was as high as 99.75%. Comparing the results of the method proposed in this paper with those of traditional algorithm, the detection accuracy was increased by 5.56%. The detection results showed that the algorithm described in this paper was effective and accurate. The work described in this paper will be utilized in the further studying on identity recognition.

The velocity of blood in vessels is an important indicator that reflects the microcirculatory status. The core of the measurement technology, which is based on spatiotemporal (ST) image, is to map the cell motion trace to the two-dimensional ST image, and transfer the measurement of flow velocity to the detection of trace orientation in ST image. This paper proposes a trace orientation measurement algorithm is based on Randomized Hough Transformation and projection transformation, and it is able to estimate trace orientation and flow velocity in noisy ST images. Experiments showed that the agreement between the results by manual and by the proposed algorithm reached over 90%.

Due to the minimum free energy model, it is very important to predict the RNA secondary structure accurately and efficiently from the suboptimal foldings. Using clustering techniques in analyzing the suboptimal structures could effectively improve the prediction accuracy. An improved k-medoids cluster method is proposed to make this a better accuracy with the RBP score and the incremental candidate set of medoids matrix in this paper. The algorithm optimizes initial medoids through an expanding medoids candidate sets gradually. The predicted results indicated this algorithm could get a higher value of CH and significantly shorten the time for calculating clustering RNA folding structures.

This paper presents a unit free-form deformation (FFD) method applied to rapid three-dimensioanl (3D) bone reconstruction, which was based on traditional FFD. With the femur as an example, we reconstructed a 3D model of femur from two X-ray images and a standardized model by taking advantage of unit FFD algorithm. The X-ray images and its parameters were taken by C-arm device. Those parameters and X-ray contour are contributed to 3D reconstruction. The out contours of X-ray image and standard model were connected by point matching algorithm. The unit-FFD lattice was built to reconstruct standard model and finally made the contour of X-ray image and standard model exactly the same. Experiments on shape accuracy, robustness and time consuming, carried out by 35 specimen from cadaver, showed that mean error of shape (0. 52 mm) and mean construction time (112 s) were lower than those using traditional method (0.7-2.6 mm, 8-20 min). The method proposed in this paper shows a good prospect in clinical application and related research.

Mitral valve disease is one of the most popular heart valve diseases. Precise positioning and displaying of the valve characteristics is necessary for the minimally invasive mitral valve repairing procedures. This paper presents a multi-resolution elastic registration method to compute the deformation functions constructed from cubic B-splines in three dimensional ultrasound images, in which the objective functional to be optimized was generated by maximum likelihood method based on the probabilistic distribution of the ultrasound speckle noise. The algorithm was then applied to register the mitral valve voxels. Numerical results proved the effectiveness of the algorithm.

This paper presents a probability segmentation algorithm for lung nodules based on three-dimensional features. Firstly, we computed intensity and texture features in region of interest (ROI) pixel by pixel to get their feature vector, and then classified all the pixels based on their feature vector. At last, we carried region growing on the classified result, and got the final segmentation result. Using the public Lung Imaging Database Consortium (LIDC) lung nodule datasets, we verified the performance of proposed method by comparing the probability map within LIDC datasets, which was drawn by four radiology doctors separately. The experimental results showed that the segmentation algorithm using three-dimensional intensity and texture features would be effective.

A non-linear rectification based on immune genetic algorithm (IGA) is proposed in this paper, for the shortcoming of the non-linearity rectification. This algorithm introducing the biologic immune mechanism into the genetic algorithm can restrain the disadvantages that the poor precision, slow convergence speed and early maturity of the genetic algorithm. Computer simulations indicated that the algorithm not only keeps population diversity, but also increases the convergent speed, precision and the stability greatly. The results have shown the correctness and effectiveness of the method.

Cardiac enlargement is an important symptom of vascular and heart disease. The cardiothoracic ratio (CTR) is an important index used to measure the size of heart. The aim of this study was to assess the relationship between aging and cardiothoracic ratio. This paper also presents an improved C-V level set method to segment lung tissue based on X-ray image, which used to automatically compute CTR. In the investigation carried out in our school, we got more than 3 120 chest radiographs from medical examination of the working population in Beijing, and we systematically studied the effects of age and gender on the CTR to obtain reference values for each group. The reference values established in this study can be useful for recording and quantifying the cardiac enlargement, so that it may be useful for calling attention to the cardiovascular diseases and the heart diseases.