Search

Falls among the elderly are a common and serious health risk that can lead to physical injuries and other complications. To promptly detect and respond to fall events, radar-based fall detection systems have gained widespread attention. In this paper, a deep learning model is proposed based on the frequency spectrum of radar signals, called the convolutional bidirectional long short-term memory (CB-LSTM) model. The introduction of the CB-LSTM model enables the fall detection system to capture both temporal sequential and spatial features simultaneously, thereby enhancing the accuracy and reliability of the detection. Extensive comparison experiments demonstrate that our model achieves an accuracy of 98.83% in detecting falls, surpassing other relevant methods currently available. In summary, this study provides effective technical support using the frequency spectrum and deep learning methods to monitor falls among the elderly through the design and experimental validation of a radar-based fall detection system, which has great potential for improving quality of life for the elderly and providing timely rescue measures. [ABSTRACT FROM AUTHOR]

Accurate segmentation of cardiac anatomy is a prerequisite for the diagnosis of cardiovascular disease. However, due to differences in imaging modalities and imaging devices, known as domain shift, the segmentation performance of deep learning models lacks reliability. In this paper, we propose a two-stage progressive unsupervised domain adaptation network (TSP-UDANet) to reduce domain shift when segmenting cardiac images from various sources. We alleviate the domain shift between the feature distribution of the source and target domains by introducing an intermediate domain as a bridge. The TSP-UDANet consists of three sub-networks: a style transfer sub-network, a segmentation sub-network, and a self-training sub-network. We conduct cooperative alignment of different domains at image level, feature level, and output level. Specifically, we transform the appearance of images across domains and enhance domain invariance by adversarial learning in multiple aspects to achieve unsupervised segmentation of the target modality. We validate the TSP-UDANet on the MMWHS (unpaired MRI and CT images), MS-CMRSeg (cross-modality MRI images), and M&Ms (cross-vendor MRI images) datasets. The experimental results demonstrate excellent segmentation performance and generalizability for unlabeled target modality images. [ABSTRACT FROM AUTHOR]

Background: Pulmonary embolism is a kind of cardiovascular disease that threatens human life and health. Since pulmonary embolism exists in the pulmonary artery, improving the segmentation accuracy of pulmonary artery is the key to the diagnosis of pulmonary embolism. Traditional medical image segmentation methods have limited effectiveness in pulmonary artery segmentation. In recent years, deep learning methods have been gradually adopted to solve complex problems in the field of medical image segmentation. Purpose: Due to the irregular shape of the pulmonary artery and the adjacent‐complex tissues, the accuracy of the existing pulmonary artery segmentation methods based on deep learning needs to be improved. Therefore, the purpose of this paper is to develop a segmentation network, which can obtain higher segmentation accuracy and further improve the diagnosis effect. Methods: In this study, the pulmonary artery segmentation performance from the network model and loss function is improved, proposing a pulmonary artery segmentation network (PA‐Net) to segment the pulmonary artery region from 2D CT images. Reverse Attention and edge attention are used to enhance the expression ability of the boundary. In addition, to better use feature information, the channel attention module is introduced in the decoder to highlight the important channel features and suppress the unimportant channels. Due to blurred boundaries, pixels near the boundaries of the pulmonary artery may be difficult to segment. Therefore, a new contour loss function based on the active contour model is proposed in this study to segment the target region by assigning dynamic weights to false positive and false negative regions and accurately predict the boundary structure. Results: The experimental results show that the segmentation accuracy of this proposed method is significantly improved in comparison with state‐of‐the‐art segmentation methods, and the Dice coefficient is 0.938 ± 0.035, which is also confirmed from the 3D reconstruction results. Conclusions: Our proposed method can accurately segment pulmonary artery structure. This new development will provide the possibility for further rapid diagnosis of pulmonary artery diseases such as pulmonary embolism. Code is available at https://github.com/Yuanyan19/PA‐Net. [ABSTRACT FROM AUTHOR]

Coronavirus disease 2019 (COVID‐19) epidemic has devastating effects on personal health around the world. It is significant to achieve accurate segmentation of pulmonary infection regions, which is an early indicator of disease. To solve this problem, a deep learning model, namely, the content‐aware pre‐activated residual UNet (CAPA‐ResUNet), was proposed for segmenting COVID‐19 lesions from CT slices. In this network, the pre‐activated residual block was used for down‐sampling to solve the problems of complex foreground and large fluctuations of distribution in datasets during training and to avoid gradient disappearance. The area loss function based on the false segmentation regions was proposed to solve the problem of fuzzy boundary of the lesion area. This model was evaluated by the public dataset (COVID‐19 Lung CT Lesion Segmentation Challenge—2020) and compared its performance with those of classical models. Our method gains an advantage over other models in multiple metrics. Such as the Dice coefficient, specificity (Spe), and intersection over union (IoU), our CAPA‐ResUNet obtained 0.775 points, 0.972 points, and 0.646 points, respectively. The Dice coefficient of our model was 2.51% higher than Content‐aware residual UNet (CARes‐UNet). The code is available at https://github.com/malu108/LungInfectionSeg. [ABSTRACT FROM AUTHOR]

Background: Many cardiovascular diseases are closely related to the composition of epicardial adipose tissue (EAT). Accurate segmentation of EAT can provide a reliable reference for doctors to diagnose the disease. The distribution and composition of EAT often have significant individual differences, and the traditional segmentation methods are not effective. In recent years, deep learning method has been gradually introduced into EAT segmentation task. Purpose: The existing EAT segmentation methods based on deep learning have a large amount of computation and the segmentation accuracy needs to be improved. Therefore, the purpose of this paper is to develop a lightweight EAT segmentation network, which can obtain higher segmentation accuracy with less computation and further alleviate the problem of false‐positive segmentation. Methods: First, the obtained computed tomography was preprocessed. That is, the threshold range of EAT was determined to be −190, −30 HU according to prior knowledge, and the non‐adipose pixels were excluded by threshold segmentation to reduce the difficulty of training. Second, the image obtained after thresholding was input into the lightweight RDU‐Net network to perform the training, validating, and testing process. RDU‐Net uses a residual multi‐scale dilated convolution block in order to extract a wider range of information without changing the current resolution. At the same time, the form of residual connection is adopted to avoid the problem of gradient expansion or gradient explosion caused by too deep network, which also makes the learning easier. In order to optimize the training process, this paper proposes PNDiceLoss, which takes both positive and negative pixels as learning targets, fully considers the class imbalance problem, and appropriately highlights the status of positive pixels. Results: In this paper, 50 CCTA images were randomly selected from the hospital, and the commonly used Dice similarity coefficient (DSC), Jaccard similarity, accuracy (ACC), specificity (SP), precision (PC), and Pearson correlation coefficient are used as evaluation metrics. Bland–Altman analysis results show that the extracted EAT volume is consistent with the actual volume. Compared with the existing methods, the segmentation results show that the proposed method achieves better performance on these metrics, achieving the DSC of 0.9262. The number of false‐positive pixels has been reduced by more than half. Pearson correlation coefficient reached 0.992, and linear regression coefficient reached 0.977 when measuring the volume of EAT obtained. In order to verify the effectiveness of the proposed method, experiments are carried out in the cardiac fat database of VisualLab. On this database, the proposed method also achieved good results, and the DSC value reached 0.927 in the case of only 878 slices. Conclusions: A new method to segment and quantify EAT is proposed. Comprehensive experiments show that compared with some classical segmentation algorithms, the proposed method has the advantages of shorter time‐consuming, less memory required for operations, and higher segmentation accuracy. The code is available at https://github.com/lvanlee/EAT_Seg/tree/main/EAT_seg. [ABSTRACT FROM AUTHOR]

Purpose: Myocardial infarction (MI) is one of the most common cardiovascular diseases, frequently resulting in death. Early and accurate diagnosis is therefore important, and the electrocardiogram (ECG) is a simple and effective method for achieving this. However, it requires assessment by a specialist; so many recent works have focused on the automatic assessment of ECG signals. Methods: For the detection and localization of MI, deep learning models have been proposed, but the diagnostic accuracy of this approaches still need to be improved. Moreover, with deep learning methods the way in which a given result was achieved lacks interpretability. In this study, ECG data was obtained from the PhysioBank open access database, and was analyzed as follows. Firstly, the 12-lead ECG signal was preprocessed to identify each beat and obtain each heart interval. Secondly, a multi-scale deep learning model combined with a residual network and attention mechanism was proposed, where the input was the 12-lead ECG recording. Through the SENet model and the Grad-CAM algorithm, the weighting of each lead was calculated and visualized. Using existing knowledge of the way in which different types of MI gave characteristic patterns in specific ECG leads, the model was used to provisionally diagnose the type of MI according to the characteristics of each of the 12 ECG leads. Results: Ten types of MI anterior, anterior lateral, anterior septal, inferior, inferior lateral, inferior posterior, inferior posterior lateral, lateral, posterior, and posterior lateral were diagnosed. The average accuracy, sensitivity, and specificity for MI detection of all lesion types was 99.98, 99.94, and 99.98%, respectively; and the average accuracy, sensitivity, and specificity for MI localization was 99.79, 99.88, and 99.98%, respectively. Conclusion: When compared to existing models based on traditional machine learning methods, convolutional neural networks and recurrent neural networks, the results showed that the proposed model had better diagnostic performance, being superior in accuracy, sensitivity, and specificity. [ABSTRACT FROM AUTHOR]

• A deep learning neural network named short-connected autoencoder long short term memory based is proposed, and successfully solved the problem in simultaneous and proportional robotic arm control. • The work specifically built a model implied the inner relationship map between the surface electromyographic signals and the joint angles of shoulder and elbow. • The proposed estimation method only requires 5 channels electromyography signal input but provides 2 channels joint angle signals on shoulder and 1 channel joint angle signals on elbow. • The average correlation coefficient of the estimated joint angle signals and the real joint angle signals reaches 95.7%. Robotic arm control has drawn a lot of attention along with the development of industrialization. The methods based on myoelectric pattern recognition have been proposed with multiple degrees of freedom for years. While these methods can support the actuation of several classes of discrete movements sequentially, they do not allow simultaneous control of multiple movements in a continuous manner like natural arms. In this study, we proposed a short connected autoencoder long short-term memory (SCA-LSTM) based simultaneous and proportional (SP) scheme that estimates continuous arm movements using kinematic information extracted from surface electromyogram (sEMG) recordings. The sEMG signals corresponding to seven classes of shoulder-elbow joint angle movements acquired from eleven participants were preprocessed using max root mean square envelope. Afterwards, the proposed SCA-LSTM model and two commonly applied models, namely, multilayer perceptrons (MLPs) and convolutional neural network (CNN), were trained and tested using the preprocessed data for continuous estimation of arm movements. Our experimental results showed that the proposed SCA-LSTM model could achieve a significantly higher estimation accuracy of approximately 95.7% that is consistently stable across the subjects in comparison to the CNN (86.8%) and MLP (83.4%) models. These results suggest that the proposed SCA-LSTM would be a promising model for continuous estimation of upper limb movements from sEMG signals for prosthetic control. [ABSTRACT FROM AUTHOR]

Automatic detection of arrhythmia is of great significance for early prevention and diagnosis of cardiovascular disease. Traditional feature engineering methods based on expert knowledge lack multidimensional and multi-view information abstraction and data representation ability, so the traditional research on pattern recognition of arrhythmia detection cannot achieve satisfactory results. Recently, with the increase of deep learning technology, automatic feature extraction of ECG data based on deep neural networks has been widely discussed. In order to utilize the complementary strength between different schemes, in this paper, we propose an arrhythmia detection method based on the multi-resolution representation (MRR) of ECG signals. This method utilizes four different up to date deep neural networks as four channel models for ECG vector representations learning. The deep learning based representations, together with hand-crafted features of ECG, forms the MRR, which is the input of the downstream classification strategy. The experimental results of big ECG dataset multi-label classification confirm that the F1 score of the proposed method is 0.9238, which is 1.31%, 0.62%, 1.18% and 0.6% higher than that of each channel model. From the perspective of architecture, this proposed method is highly scalable and can be employed as an example for arrhythmia recognition. [ABSTRACT FROM AUTHOR]

Electromyography (EMG) plays a vital role in detecting medical abnormalities and analyzing the biomechanics of human or animal movements. However, long-term EMG signal monitoring will increase the bandwidth requirements and transmission system burden. Compressed sensing (CS) is attractive for resource-limited EMG signal monitoring. However, traditional CS reconstruction algorithms require prior knowledge of the signal, and the reconstruction process is inefficient. To solve this problem, this paper proposed a reconstruction algorithm based on deep learning, which combines the Temporal Convolutional Network (TCN) and the fully connected layer to learn the mapping relationship between the compressed measurement value and the original signal, and it has been verified in the Ninapro database. The results show that, for the same subject, compared with the traditional reconstruction algorithms orthogonal matching pursuit (OMP), basis pursuit (BP), and Modified Compressive Sampling Matching Pursuit (MCo), the reconstruction quality and efficiency of the proposed method is significantly improved under various compression ratios (CR). • Solve the problem of poor compressed sensing reconstruction effect of EMG. • Propose a novel EMG compressed sensing reconstruction method TCNN. • TCNN improves the reconstruction quality and efficiency of EMG. • Obtain the most suitable compressed ratio for EMG recovery. [ABSTRACT FROM AUTHOR]