Graph-based EEG approach for depression prediction: integrating time-frequency complexity and spatial topology.

Depression has become the prevailing global mental health concern. The accuracy of traditional depression diagnosis methods faces challenges due to diverse factors, making primary identification a complex task. Thus, the imperative lies in developing a method that fulfills objectivity and effectiveness criteria for depression identification. Current research underscores notable disparities in brain activity between individuals with depression and those without. The Electroencephalogram (EEG), as a biologically reflective and easily accessible signal, is widely used to diagnose depression. This article introduces an innovative depression prediction strategy that merges time-frequency complexity and electrode spatial topology to aid in depression diagnosis. Initially, time-frequency complexity and temporal features of the EEG signal are extracted to generate node features for a graph convolutional network. Subsequently, leveraging channel correlation, the brain network adjacency matrix is employed and calculated. The final depression classification is achieved by training and validating a graph convolutional network with graph node features and a brain network adjacency matrix based on channel correlation. The proposed strategy has been validated using two publicly available EEG datasets, MODMA and PRED+CT, achieving notable accuracy rates of 98.30 and 96.51%, respectively. These outcomes affirm the reliability and utility of our proposed strategy in predicting depression using EEG signals. Additionally, the findings substantiate the effectiveness of EEG time-frequency complexity characteristics as valuable biomarkers for depression prediction.

Magneto-acousto-electrical tomography using nonlinearly frequency-modulated ultrasound.

Objective. In this study, nonlinearly frequency-modulated (NLFM) ultrasound was applied to magneto-acousto-electrical tomography (MAET) to increase the dynamic range of detection.Approach. Generation of NLFM signals using window function method-based on the principle of stationary phase-and piecewise linear frequency modulation method-based on the genetic algorithm-was discussed. The MAET experiment systems using spike, linearly frequency-modulated (LFM), or NLFM pulse stimulation were constructed, and three groups of MAET experiments on saline agar phantom samples were carried out to verify the performance-respectively the sensitivity, the dynamic range, and the longitudinal resolution of detection-of MAET using NLFM ultrasound in comparison to that using LFM ultrasound. Based on the above experiments, a pork sample was imaged by ultrasound imaging method, spike MAET method, LFM MAET method, and NLFM MAET method, to compare the imaging accuracy.Main results. The experiment results showed that, through sacrificing very little main-lobe width of pulse compression or equivalently the longitudinal resolution, the MAET using NLFM ultrasound achieved higher signal-to-interference ratio (and therefore higher detection sensitivity), lower side-lobe levels of pulse compression (and therefore larger dynamic range of detection), and large anti-interference capability, compared to the MAET using LFM ultrasound.Significance. The applicability of the MAET using NLFM ultrasound was proved in circumferences where sensitivity and dynamic range of detection were mostly important and slightly lower longitudinal resolution of detection was acceptable. The study furthered the scheme of using coded ultrasound excitation toward the clinical application of MAET.

Selfrec-Net: self-supervised deep learning approach for the reconstruction of Cherenkov-excited luminescence scanned tomography.

As an emerging imaging technique, Cherenkov-excited luminescence scanned tomography (CELST) can recover a high-resolution 3D distribution of quantum emission fields within tissue using X-ray excitation for deep penetrance. However, its reconstruction is an ill-posed and under-conditioned inverse problem because of the diffuse optical emission signal. Deep learning based image reconstruction has shown very good potential for solving these types of problems, however they suffer from a lack of ground-truth image data to confirm when used with experimental data. To overcome this, a self-supervised network cascaded by a 3D reconstruction network and the forward model, termed Selfrec-Net, was proposed to perform CELST reconstruction. Under this framework, the boundary measurements are input to the network to reconstruct the distribution of the quantum field and the predicted measurements are subsequently obtained by feeding the reconstructed result to the forward model. The network was trained by minimizing the loss between the input measurements and the predicted measurements rather than the reconstructed distributions and the corresponding ground truths. Comparative experiments were carried out on both numerical simulations and physical phantoms. For singular luminescent targets, the results demonstrate the effectiveness and robustness of the proposed network, and comparable performance can be attained to a state-of-the-art deep supervised learning algorithm, where the accuracy of the emission yield and localization of the objects was far superior to iterative reconstruction methods. Reconstruction of multiple objects is still reasonable with high localization accuracy, although with limits to the emission yield accuracy as the distribution becomes more complex. Overall though the reconstruction of Selfrec-Net provides a self-supervised way to recover the location and emission yield of molecular distributions in murine model tissues.

A temporal multi-scale hybrid attention network for sleep stage classification.

Sleep is crucial for human health. Automatic sleep stage classification based on polysomnogram (PSG) is meaningful for the diagnosis of sleep disorders, which has attracted extensive attention in recent years. Most existing methods could not fully consider the different transitions of sleep stages and fit the visual inspection of sleep experts simultaneously. To this end, we propose a temporal multi-scale hybrid attention network, namely TMHAN, to automatically achieve sleep staging. The temporal multi-scale mechanism incorporates short-term abrupt and long-term periodic transitions of the successive PSG epochs. Furthermore, the hybrid attention mechanism includes 1-D local attention, 2-D global attention, and 2-D contextual sparse multi-head self-attention for three kinds of sequence-level representations. The concatenated representation is subsequently fed into a softmax layer to train an end-to-end model. Experimental results on two benchmark sleep datasets show that TMHAN obtains the best performance compared with several baselines, demonstrating the effectiveness of our model. In general, our work not only provides good classification performance, but also fits the actual sleep staging processes, which makes contribution for the combination of deep learning and sleep medicine.

X-ray Cherenkov-luminescence tomography reconstruction with a three-component deep learning algorithm: Swin transformer, convolutional neural network, and locality module.

Significance: X-ray Cherenkov-luminescence tomography (XCLT) produces fast emission data from megavoltage (MV) x-ray scanning, in which the excitation location of molecules within tissue is reconstructed. However standard filtered backprojection (FBP) algorithms for XCLT sinogram reconstruction can suffer from insufficient data due to dose limitations, so there are limits in the reconstruction quality with some artifacts. We report a deep learning algorithm for XCLT with high image quality and improved quantitative accuracy. Aim: To directly reconstruct the distribution of emission quantum yield for x-ray Cherenkov-luminescence tomography, we proposed a three-component deep learning algorithm that includes a Swin transformer, convolution neural network, and locality module model. Approach: A data-to-image model x-ray Cherenkov-luminescence tomography is developed based on a Swin transformer, which is used to extract pixel-level prior information from the sinogram domain. Meanwhile, a convolutional neural network structure is deployed to transform the extracted pixel information from the sinogram domain to the image domain. Finally, a locality module is designed between the encoder and decoder connection structures for delivering features. Its performance was validated with simulation, physical phantom, and in vivo experiments. Results: This approach can better deal with the limits to data than conventional FBP methods. The method was validated with numerical and physical phantom experiments, with results showing that it improved the reconstruction performance mean square error ( > 94.1 % ), peak signal-to-noise ratio ( > 41.7 % ), and Pearson correlation ( > 19 % ) compared with the FBP algorithm. The Swin-CNN also achieved a 32.1% improvement in PSNR over the deep learning method AUTOMAP. Conclusions: This study shows that the three-component deep learning algorithm provides an effective reconstruction method for x-ray Cherenkov-luminescence tomography.

A Depression Prediction Algorithm Based on Spatiotemporal Feature of EEG Signal.

Depression has gradually become the most common mental disorder in the world. The accuracy of its diagnosis may be affected by many factors, while the primary diagnosis seems to be difficult to define. Finding a way to identify depression by satisfying both objective and effective conditions is an urgent issue. In this paper, a strategy for predicting depression based on spatiotemporal features is proposed, and is expected to be used in the auxiliary diagnosis of depression. Firstly, electroencephalogram (EEG) signals were denoised through the filter to obtain the power spectra of the three corresponding frequency ranges, Theta, Alpha and Beta. Using orthogonal projection, the spatial positions of the electrodes were mapped to the brainpower spectrum, thereby obtaining three brain maps with spatial information. Then, the three brain maps were superimposed on a new brain map with frequency domain and spatial characteristics. A Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) were applied to extract the sequential feature. The proposed strategy was validated with a public EEG dataset, achieving an accuracy of 89.63% and an accuracy of 88.56% with the private dataset. The network had less complexity with only six layers. The results show that our strategy is credible, less complex and useful in predicting depression using EEG signals.

Deep-learning based image reconstruction for MRI-guided near-infrared spectral tomography.

Non-invasive near-infrared spectral tomography (NIRST) can incorporate the structural information provided by simultaneous magnetic resonance imaging (MRI), and this has significantly improved the images obtained of tissue function. However, the process of MRI guidance in NIRST has been time consuming because of the needs for tissue-type segmentation and forward diffuse modeling of light propagation. To overcome these problems, a reconstruction algorithm for MRI-guided NIRST based on deep learning is proposed and validated by simulation and real patient imaging data for breast cancer characterization. In this approach, diffused optical signals and MRI images were both used as the input to the neural network, and simultaneously recovered the concentrations of oxy-hemoglobin, deoxy-hemoglobin, and water via end-to-end training by using 20,000 sets of computer-generated simulation phantoms. The simulation phantom studies showed that the quality of the reconstructed images was improved, compared to that obtained by other existing reconstruction methods. Reconstructed patient images show that the well-trained neural network with only simulation data sets can be directly used for differentiating malignant from benign breast tumors.

Exercise Training Increases Resting Calf Muscle Oxygen Metabolism in Patients with Peripheral Artery Disease.

Exercise training can mitigate symptoms of claudication (walking-induced muscle pain) in patients with peripheral artery disease (PAD). One adaptive response enabling this improvement is enhanced muscle oxygen metabolism. To explore this issue, we used arterial-occlusion diffuse optical spectroscopy (AO-DOS) to measure the effects of exercise training on the metabolic rate of oxygen (MRO2) in resting calf muscle. Additionally, venous-occlusion DOS (VO-DOS) and frequency-domain DOS (FD-DOS) were used to measure muscle blood flow (F) and tissue oxygen saturation (StO2), and resting calf muscle oxygen extraction fraction (OEF) was calculated from MRO2, F, and blood hemoglobin. Lastly, the venous/arterial ratio (γ) of blood monitored by FD-DOS was calculated from OEF and StO2. PAD patients who experience claudication (n = 28) were randomly assigned to exercise and control groups. Patients in the exercise group received 3 months of supervised exercise training. Optical measurements were obtained at baseline and at 3 months in both groups. Resting MRO2, OEF, and F, respectively, increased by 30% (12%, 44%) (p < 0.001), 17% (6%, 45%) (p = 0.003), and 7% (0%, 16%) (p = 0.11), after exercise training (median (interquartile range)). The pre-exercise γ was 0.76 (0.61, 0.89); it decreased by 12% (35%, 6%) after exercise training (p = 0.011). Improvement in exercise performance was associated with a correlative increase in resting OEF (R = 0.45, p = 0.02).

Quantification of blood flow index in diffuse correlation spectroscopy using long short-term memory architecture.

Diffuse correlation spectroscopy (DCS) is a noninvasive technique that derives blood flow information from measurements of the temporal intensity fluctuations of multiply scattered light. Blood flow index (BFI) and especially its variation was demonstrated to be approximately proportional to absolute blood flow. We investigated and assessed the utility of a long short-term memory (LSTM) architecture for quantification of BFI in DCS. Phantom and in vivo experiments were established to measure normalized intensity autocorrelation function data. Improved accuracy and faster computational time were gained by the proposed LSTM architecture. The results support the notion of using proposed LSTM architecture for quantification of BFI in DCS. This approach would be especially useful for continuous real-time monitoring of blood flow.

[A hybrid attention temporal sequential network for sleep stage classification].

Sleep stage classification is a necessary fundamental method for the diagnosis of sleep diseases, which has attracted extensive attention in recent years. Traditional methods for sleep stage classification, such as manual marking methods and machine learning algorithms, have the limitations of low efficiency and defective generalization. Recently, deep neural networks have shown improved results by the capability of learning complex pattern in the sleep data. However, these models ignore the intra-temporal sequential information and the correlation among all channels in each segment of the sleep data. To solve these problems, a hybrid attention temporal sequential network model is proposed in this paper, choosing recurrent neural network to replace traditional convolutional neural network, and extracting temporal features of polysomnography from the perspective of time. Furthermore, intra-temporal attention mechanism and channel attention mechanism are adopted to achieve the fusion of the intra-temporal representation and the fusion of channel-correlated representation. And then, based on recurrent neural network and inter-temporal attention mechanism, this model further realized the fusion of inter-temporal contextual representation. Finally, the end-to-end automatic sleep stage classification is accomplished according to the above hybrid representation. This paper evaluates the proposed model based on two public benchmark sleep datasets downloaded from open-source website, which include a number of polysomnography. Experimental results show that the proposed model could achieve better performance compared with ten state-of-the-art baselines. The overall accuracy of sleep stage classification could reach 0.801, 0.801 and 0.717, respectively. Meanwhile, the macro average F1-scores of the proposed model could reach 0.752, 0.728 and 0.700. All experimental results could demonstrate the effectiveness of the proposed model.

End-to-end Res-Unet based reconstruction algorithm for photoacoustic imaging.

Recently, deep neural networks have attracted great attention in photoacoustic imaging (PAI). In PAI, reconstructing the initial pressure distribution from acquired photoacoustic (PA) signals is a typically inverse problem. In this paper, an end-to-end Unet with residual blocks (Res-Unet) is designed and trained to solve the inverse problem in PAI. The performance of the proposed algorithm is explored and analyzed by comparing a recent model-resolution-based regularization algorithm (MRR) with numerical and physical phantom experiments. The improvement obtained in the reconstructed images was more than 95% in pearson correlation and 39% in peak signal-to-noise ratio in comparison to the MRR. The Res-Unet also achieved superior performance over the state-of-the-art Unet++ architecture by more than 18% in PSNR in simulation experiments.

State-of-the-Art CNN Optimizer for Brain Tumor Segmentation in Magnetic Resonance Images.

Brain tumors have become a leading cause of death around the globe. The main reason for this epidemic is the difficulty conducting a timely diagnosis of the tumor. Fortunately, magnetic resonance images (MRI) are utilized to diagnose tumors in most cases. The performance of a Convolutional Neural Network (CNN) depends on many factors (i.e., weight initialization, optimization, batches and epochs, learning rate, activation function, loss function, and network topology), data quality, and specific combinations of these model attributes. When we deal with a segmentation or classification problem, utilizing a single optimizer is considered weak testing or validity unless the decision of the selection of an optimizer is backed up by a strong argument. Therefore, optimizer selection processes are considered important to validate the usage of a single optimizer in order to attain these decision problems. In this paper, we provides a comprehensive comparative analysis of popular optimizers of CNN to benchmark the segmentation for improvement. In detail, we perform a comparative analysis of 10 different state-of-the-art gradient descent-based optimizers, namely Adaptive Gradient (Adagrad), Adaptive Delta (AdaDelta), Stochastic Gradient Descent (SGD), Adaptive Momentum (Adam), Cyclic Learning Rate (CLR), Adaptive Max Pooling (Adamax), Root Mean Square Propagation (RMS Prop), Nesterov Adaptive Momentum (Nadam), and Nesterov accelerated gradient (NAG) for CNN. The experiments were performed on the BraTS2015 data set. The Adam optimizer had the best accuracy of 99.2% in enhancing the CNN ability in classification and segmentation.

A hybrid self-attention deep learning framework for multivariate sleep stage classification.

BACKGROUND: Sleep is a complex and dynamic biological process characterized by different sleep patterns. Comprehensive sleep monitoring and analysis using multivariate polysomnography (PSG) records has achieved significant efforts to prevent sleep-related disorders. To alleviate the time consumption caused by manual visual inspection of PSG, automatic multivariate sleep stage classification has become an important research topic in medical and bioinformatics. RESULTS: We present a unified hybrid self-attention deep learning framework, namely HybridAtt, to automatically classify sleep stages by capturing channel and temporal correlations from multivariate PSG records. We construct a new multi-view convolutional representation module to learn channel-specific and global view features from the heterogeneous PSG inputs. The hybrid attention mechanism is designed to further fuse the multi-view features by inferring their dependencies without any additional supervision. The learned attentional representation is subsequently fed through a softmax layer to train an end-to-end deep learning model. CONCLUSIONS: We empirically evaluate our proposed HybridAtt model on a benchmark PSG dataset in two feature domains, referred to as the time and frequency domains. Experimental results show that HybridAtt consistently outperforms ten baseline methods in both feature spaces, demonstrating the effectiveness of HybridAtt in the task of sleep stage classification.

FusionAtt: Deep Fusional Attention Networks for Multi-Channel Biomedical Signals.

Recently, pervasive sensing technologies have been widely applied to comprehensive patient monitoring in order to improve clinical treatment. Various types of biomedical signals collected by different sensing channels provide different aspects of patient health information. However, due to the uncertainty and variability in clinical observation, not all the channels are relevant and important to the target task. Thus, in order to extract informative representations from multi-channel biosignals, channel awareness has become a key enabler for deep learning in biosignal processing and has attracted increasing research interest in health informatics. Towards this end, we propose FusionAtt-a deep fusional attention network that can learn channel-aware representations of multi-channel biosignals, while preserving complex correlations among all the channels. FusionAtt is able to dynamically quantify the importance of each biomedical channel, and relies on more informative ones to enhance feature representation in an end-to-end manner. We empirically evaluated FusionAtt in two clinical tasks: multi-channel seizure detection and multivariate sleep stage classification. Experimental results showed that FusionAtt consistently outperformed the state-of-the-art models in four different evaluation measurements, demonstrating the effectiveness of the proposed fusional attention mechanism.

A Multi-View Deep Learning Framework for EEG Seizure Detection.

The recent advances in pervasive sensing technologies have enabled us to monitor and analyze the multi-channel electroencephalogram (EEG) signals of epilepsy patients to prevent serious outcomes caused by epileptic seizures. To avoid manual visual inspection from long-term EEG readings, automatic EEG seizure detection has garnered increasing attention among researchers. In this paper, we present a unified multi-view deep learning framework to capture brain abnormalities associated with seizures based on multi-channel scalp EEG signals. The proposed approach is an end-to-end model that is able to jointly learn multi-view features from both unsupervised multi-channel EEG reconstruction and supervised seizure detection via spectrogram representation. We construct a new autoencoder-based multi-view learning model by incorporating both inter and intra correlations of EEG channels to unleash the power of multi-channel information. By adding a channel-wise competition mechanism in the training phase, we propose a channel-aware seizure detection module to guide our multi-view structure to focus on important and relevant EEG channels. To validate the effectiveness of the proposed framework, extensive experiments against nine baselines, including both traditional handcrafted feature extraction and conventional deep learning methods, are carried out on a benchmark scalp EEG dataset. Experimental results show that the proposed model is able to achieve higher average accuracy and f1-score at 94.37% and 85.34%, respectively, using 5-fold subject-independent cross validation, demonstrating a powerful and effective method in the task of EEG seizure detection.

Back-propagation neural network-based reconstruction algorithm for diffuse optical tomography.

Diffuse optical tomography (DOT) is a promising noninvasive imaging modality and is capable of providing functional characteristics of biological tissue by quantifying optical parameters. The DOT image reconstruction is ill-posed and ill-conditioned, due to the highly diffusive nature of light propagation in biological tissues and limited boundary measurements. The widely used regularization technique for DOT image reconstruction is Tikhonov regularization, which tends to yield oversmoothed and low-quality images containing severe artifacts. It is necessary to accurately choose a regularization parameter for Tikhonov regularization. To overcome these limitations, we develop a noniterative reconstruction method, whereby optical properties are recovered based on a back-propagation neural network (BPNN). We train the parameters of BPNN before DOT image reconstruction based on a set of training data. DOT image reconstruction is achieved by implementing a single evaluation of the trained network. To demonstrate the performance of the proposed algorithm, we compare with the conventional Tikhonov regularization-based reconstruction method. The experimental results demonstrate that image quality and quantitative accuracy of reconstructed optical properties are significantly improved with the proposed algorithm.

A multi-context learning approach for EEG epileptic seizure detection.

BACKGROUND: Epilepsy is a neurological disease characterized by unprovoked seizures in the brain. The recent advances in sensor technologies allow researchers to analyze the collected biological records to improve the treatment of epilepsy. Electroencephalogram (EEG) is the most commonly used biological measurement to effectively capture the abnormalities of different brain areas during the EEG seizures. To avoid manual visual inspection from long-term EEG readings, automatic epileptic EEG seizure detection has become an important research issue in bioinformatics. RESULTS: We present a multi-context learning approach to automatically detect EEG seizures by incorporating a feature fusion strategy. We generate EEG scalogram sequences from the EEG records by utilizing waveform transform to describe the frequency content over time. We propose a multi-stage unsupervised model that integrates the features extracted from the global handcrafted engineering, channel-wise deep learning, and EEG embeddings, respectively. The learned multi-context features are subsequently merged to train a seizure detector. CONCLUSIONS: To validate the effectiveness of the proposed approach, extensive experiments against several baseline methods are carried out on two benchmark biological datasets. The experimental results demonstrate that the representative context features from multiple perspectives can be learned by the proposed model, and further improve the performance for the task of EEG seizure detection.

Bayesian sparse-based reconstruction in bioluminescence tomography improves localization accuracy and reduces computational time.

Bioluminescence tomography (BLT) provides fundamental insight into biological processes in vivo. To fully realize its potential, it is important to develop image reconstruction algorithms that accurately visualize and quantify the bioluminescence signals taking advantage of limited boundary measurements. In this study, a new 2-step reconstruction method for BLT is developed by taking advantage of the sparse a priori information of the light emission using multispectral measurements. The first step infers a wavelength-dependent prior by using all multi-wavelength measurements. The second step reconstructs the source distribution based on this developed prior. Simulation, phantom and in vivo results were performed to assess and compare the accuracy and the computational efficiency of this algorithm with conventional sparsity-promoting BLT reconstruction algorithms, and results indicate that the position errors are reduced from a few millimeters down to submillimeter, and reconstruction time is reduced by 3 orders of magnitude in most cases, to just under a few seconds. The recovery of single objects and multiple (2 and 3) small objects is simulated, and the recovery of images of a mouse phantom and an experimental animal with an existing luminescent source in the abdomen is demonstrated. Matlab code is available at https://github.com/jinchaofeng/code/tree/master.

A Review of Ultrasound Tissue Characterization with Mean Scatterer Spacing.

Tissues exhibiting quasi-periodic structures can be modeled as a collection of diffuse scatterers and coherent scatterers. The mean scatterer spacing (MSS) of coherent and quasi-periodic components is directly related to tissue microstructure and has become an important quantitative ultrasound (QUS) parameter in the characterization of quasi-periodic tissues. In this paper, a review of the literature on the development of MSS as a QUS parameter was conducted. First, a unified theoretical background of MSS estimates was provided. Then, the application of MSS estimates was summarized with respect to liver, spleen, breast, bone, muscle, and other tissues. MSS estimation techniques were applied to (a) the diagnosis of hepatitis, liver fibrosis and cirrhosis, and lesions in tissues such as liver, breast, and spleen; (b) the differentiation between benign and malignant breast tumors, and the grading of breast cancer; (c) the detection of cancellous bone; and (d) the monitoring of the efficacy of treatments such as thermal ablation, with various levels of success. Future developments were also discussed in terms of real-time implementation of MSS estimates, local MSS estimation, relationship of MSS to other QUS parameters, combination of MSS with other QUS parameters, in vivo validation of MSS estimates, MSS parametric imaging, and three-dimensional ultrasound tissue characterization.

Medical Ultrasound Video Coding with H.265/HEVC Based on ROI Extraction.

High-efficiency video compression technology is of primary importance to the storage and transmission of digital medical video in modern medical communication systems. To further improve the compression performance of medical ultrasound video, two innovative technologies based on diagnostic region-of-interest (ROI) extraction using the high efficiency video coding (H.265/HEVC) standard are presented in this paper. First, an effective ROI extraction algorithm based on image textural features is proposed to strengthen the applicability of ROI detection results in the H.265/HEVC quad-tree coding structure. Second, a hierarchical coding method based on transform coefficient adjustment and a quantization parameter (QP) selection process is designed to implement the otherness encoding for ROIs and non-ROIs. Experimental results demonstrate that the proposed optimization strategy significantly improves the coding performance by achieving a BD-BR reduction of 13.52% and a BD-PSNR gain of 1.16 dB on average compared to H.265/HEVC (HM15.0). The proposed medical video coding algorithm is expected to satisfy low bit-rate compression requirements for modern medical communication systems.