Hao Yang

Acupuncture, a key therapeutic method in traditional Chinese medicine (TCM), has been widely adopted in various clinical fields. Quantitative research on acupuncture manipulation parameters is critical for achieving standardized techniques. However, quantitative mechanical detection of acupuncture parameters remains limited. In this study, a kinematic and dynamic model of acupuncture is established, and key parameters such as the lifting-thrusting force, acceleration, velocity, and displacement, as well as the twirling-rotating angular velocity and angle, are identified. To measure these critical parameters, we propose a quantitative system comprising a sensing needle equipped with a force sensor and an inertial measurement unit (IMU), as well as an external camera module to capture image information. By fusing visual and IMU data, we can accurately identify the stationary or motion states of the needle, enabling segmented computation of the lifting-thrusting velocity and displacement. The experimental results demonstrate that the sensing needle achieves comprehensive detection with high precision, featuring an accuracy of 0.45% in force measurement and an RMSE of 1.2 mm in displacement. The extracted parameters provide an objective description of the operational characteristics and motion patterns of the four basic acupuncture manipulations and two auxiliary manipulations. These findings provide valuable tools and methods for research on acupuncture standardization.

Auscultation of the chest is a fundamental diagnostic tool for cardiovascular and pulmonary diseases. However, the two main chest sound parts, heart sound (HS) and lung sound (LS), are often mixed, limiting diagnostic accuracy. This paper presents a novel Phase-Enhanced Neural Network (PENN) for HS and LS separation. To address the under-utilization of phase information, PENN integrates a feedforward connection that feeds the input spectrum into the Restorer, enabling phase recovery based on the local inference feature of phase. A time-frequency Dual-Path Transformer (DPT) is employed to expand the network's receptive field and enhance performance. To interpret the effectiveness of PENN, two new metrics, mSI-SDRi and pSI-SDRi, are proposed to separately evaluate the contributions of magnitude and phase. Experiments show that PENN achieves pSI-SDRi improvements of 1.44 dB for HS and 2.25 dB for LS under a LS cutoff frequency ($f_{c\text{lung}}$) of 60Hz. Extensive experimental results demonstrate the effectiveness and robustness of PENN, offering a promising solution to improve the accuracy of auscultation.

Acupuncture, one of the key therapeutic methods in Traditional Chinese Medicine (TCM), has been widely adopted in various clinical fields. Quantitative research on acupuncture manipulation parameters is critical to achieve standardized techniques. However, quantitative mechanical detection of acupuncture parameters remains limited. This study establishes a kinematic and dynamic model of acupuncture, identifying key parameters such as lifting-thrusting force, acceleration, velocity, displacement, as well as twirling-rotating angular velocity and angle. To measure these critical parameters, we propose a quantitative system comprising a sensing needle equipped with a force sensor and an inertial measurement unit (IMU), as well as an external camera module to capture image information. By fusing visual and IMU data, we accurately identify the stationary or motion states of the needle, enabling segmented computation of lifting-thrusting velocity and displacement. The experimental results demonstrate that the sensing needle achieves comprehensive detection with high precision, featuring a nonlinearity error of 0.45% in force measurement and an RMSE of 1.2 mm in displacement. The extracted parameters provide an objective description of the operational characteristics and motion patterns of the four basic acupuncture manipulations. These findings provide valuable tools and methods for research in acupuncture standardization.

Tongue diagnosis is a crucial method in traditional Chinese medicine (TCM) for obtaining information about a patient’s health condition. In this study, we propose a tongue image segmentation method based on deep learning and a pixel-level tongue color classification method utilizing machine learning techniques such as support vector machine (SVM) and ridge regression. These two approaches together form a comprehensive framework that spans from tongue image acquisition to segmentation and analysis. This framework provides an objective and visualized representation of pixel-wise classification and proportion distribution within tongue images, effectively assisting TCM practitioners in diagnosing tongue conditions. It mitigates the reliance on subjective observations in traditional tongue diagnosis, reducing human bias and enhancing the objectivity of TCM diagnosis. The proposed framework consists of three main components: tongue image segmentation, pixel-wise classification, and tongue color classification. In the segmentation stage, we integrate the Segment Anything Model (SAM) into the overall segmentation network. This approach not only achieves an intersection over union (IoU) score above 0.95 across three tongue image datasets but also significantly reduces the labor-intensive annotation process required for training traditional segmentation models while improving the generalization capability of the segmentation model. For pixel-wise classification, we propose a lightweight pixel classification model based on SVM, achieving a classification accuracy of 92%. In the tongue color classification stage, we introduce a ridge regression model that classifies tongue color based on the proportion of different pixel categories. Using this method, the classification accuracy reaches 91.80%. The proposed approach enables accurate and efficient tongue image segmentation, provides an intuitive visualization of tongue color distribution, and objectively analyzes and quantifies the proportion of different tongue color categories. In the future, this framework holds potential for validation and optimization in clinical practice.

This study investigates the feasibility of using traditional Chinese medicine (TCM) tongue features for diagnosing coronary heart disease (CHD). The aim is to propose an improved prediction method for CHD diagnosis. We collected data from 255 CHD patients and 308 non-CHD patients, including basic information and tongue image data. Using nine classic classifiers such as XGBoost and Random Forest, we evaluated their performance. To enhance prediction accuracy, we introduced an improved stacking model based on feature partitioning. This model partitions the data through a two-layer network, where the first layer extracts distribution features, and the second layer performs the final prediction. The results show that the proposed method achieved an F1 score of 85.20%, an AUC of 86.00%, a recall rate of 88.46%, an accuracy of 85.80%, a precision of 82.10%, an LR + of 5.39, and an LR- of 0.14. These findings suggest that using tongue image data for CHD prediction is effective, and the proposed method could serve as a valuable tool for non-invasive early detection, warranting further research and validation.

In response to the application scenarios of modernized Traditional Chinese Medicine (TCM) diagnostic and treatment equipment moving towards the user end, an effort has been made to enhance the user-friendliness of TCM diagnostic and treatment devices. This involves introducing the concept of edge computing into the mobile tongue diagnosis instrument, shifting the tasks of tongue image acquisition and analysis to portable auxiliary diagnostic devices. To improve the efficiency of edge computing devices in handling tongue image analysis tasks, a multi-task network model based on a lightweight network backbone is proposed. The model utilizes the lightweight feature extraction backbone of MobileNet to provide feature encoding for both the semantic segmentation branch and the multi-label classification branch. The semantic segmentation branch adopts a skip-layer connection structure with multi-scale feature maps, and an attention mechanism is incorporated into the classification branch to fuse the feature maps from the segmentation branch. This achieves tongue segmentation and multi-label classification tasks in a computationally efficient environment. The model achieves a pixel accuracy of 85.3% in semantic segmentation and an accuracy of 95.6% in multi-label classification. The network’s forward propagation speed on edge computing platforms reaches 7 frames per second (FPS). The proposed lightweight network backbone multi-task network model ensures a significant improvement in processing efficiency while maintaining the accuracy of segmentation and classification tasks. Additionally, the model exhibits advantages in terms of quantity and scale, saving both storage and computational resources. It not only enhances the accuracy and efficiency of tongue image real-time analysis in edge computing scenarios but also reduces the processing time, providing excellent precision and inference speed.

Abnormalities in cardiac function arise irregularly and typically involve multimodal electrical, mechanical vibrations, and acoustics alterations. This paper proposes an Electro-Mechano-Acoustic (EMA) activity model for mapping the complete macroscopic cardiac function to refine the systematic interpretation of cardiac multimodal assessment. We abstract this activity pattern and build the mapping system by analyzing the functional comparison of the heart pump and Electronic Fuel Injection (EFI) system from the multimodal characteristics of the heart. Electrocardiogram (ECG), seismocardiogram (SCG) & Ultra-Low Frequency seismocardiogram (ULF-SCG), and Phonocardiogram (PCG) are selected to implement the EMA mapping respectively. First, a novel low-frequency cardiograph compound sensor capable of extracting both SCG and ULF-SCG is proposed, which is integrated with ECG and PCG modules on a single hardware device for portable dynamic acquisition. Afterward, a multimodal signal processing chain further analyses the acquired synchronized signals, and the extracted ULF-SCG is shown to indicate changes in heart volume. In particular, the proposed method based on waveform curvature is used to extract 9 feature points of the SCG signal, and the overall recognition accuracy reaches over 90% in the data collected by EMA portable device. Ultimately, we integrate the portable device and signal processing chains to form the EMA cardiovascular mapping system (EMACMS). As a next-generation system solution for cardiac daily dynamic monitoring, which can map the mechanical coupling and electromechanical coupling process, extract multi-characteristic heart rate variability (HRV), and enable extraction of important time intervals of cardiac activity to assess cardiac function.

Three-dimensional face analysis is now a hot research topic in computer vision. The acquisition of 3D faces requires acquiring multi-view face and obtaining them by point cloud registration. In this paper, a deep learning method is introduced in the multi-view RGBD depth sensor system to acquire matching point pairs of image data. Thus, 3D spatial point pairs are obtained. Then, the initial poses between the point clouds of multi-view faces are obtained by rigid body transformation estimation, and the coarse registration of the point clouds is completed. On this basis, for fine registration of multi-view 3D face point clouds using the Iterative Closest Point (ICP) algorithm, this paper proposes a method to convert partially overlapping point cloud registration into sub-region point cloud registration through facial region positioning. In this letter, the maximum value of RMSE for the experimental results of point cloud coarse registration is 2.26 mm with the mean and standard deviation of 1.18 ± 0.33 mm; the maximum value of RMSE for the experimental results of point cloud fine registration is 1.47 mm with the mean and standard deviation of 0.91 ± 0.14 mm. It is confirmed that the proposed method is very robust and effective for the registration of multi-view 3D face point clouds.