Avionics Module Fault Diagnosis Algorithm Based on Hybrid Attention Adaptive Multi-Scale Temporal Convolution Network.

Since the reliability of the avionics module is crucial for aircraft safety, the fault diagnosis and health management of this module are particularly significant. While deep learning-based prognostics and health management (PHM) methods exhibit highly accurate fault diagnosis, they have disadvantages such as inefficient data feature extraction and insufficient generalization capability, as well as a lack of avionics module fault data. Consequently, this study first employs fault injection to simulate various fault types of the avionics module and performs data enhancement to construct the P2020 communications processor fault dataset. Subsequently, a multichannel fault diagnosis method, the Hybrid Attention Adaptive Multi-scale Temporal Convolution Network (HAAMTCN) for the integrated functional circuit module of the avionics module, is proposed, which adaptively constructs the optimal size of the convolutional kernel to efficiently extract features of avionics module fault signals with large information entropy. Further, the combined use of the Interaction Channel Attention (ICA) module and the Hierarchical Block Temporal Attention (HBTA) module results in the HAAMTCN to pay more attention to the critical information in the channel dimension and time step dimension. The experimental results show that the HAAMTCN achieves an accuracy of 99.64% in the avionics module fault classification task which proves our method achieves better performance in comparison with existing methods.

Fractional Fourier Image Transformer for Multimodal Remote Sensing Data Classification.

With the recent development of the joint classification of hyperspectral image (HSI) and light detection and ranging (LiDAR) data, deep learning methods have achieved promising performance owing to their locally sematic feature extracting ability. Nonetheless, the limited receptive field restricted the convolutional neural networks (CNNs) to represent global contextual and sequential attributes, while visual image transformers (VITs) lose local semantic information. Focusing on these issues, we propose a fractional Fourier image transformer (FrIT) as a backbone network to extract both global and local contexts effectively. In the proposed FrIT framework, HSI and LiDAR data are first fused at the pixel level, and both multisource feature and HSI feature extractors are utilized to capture local contexts. Then, a plug-and-play image transformer FrIT is explored for global contextual and sequential feature extraction. Unlike the attention-based representations in classic VIT, FrIT is capable of speeding up the transformer architectures massively and learning valuable contextual information effectively and efficiently. More significantly, to reduce redundancy and loss of information from shallow to deep layers, FrIT is devised to connect contextual features in multiple fractional domains. Five HSI and LiDAR scenes including one newly labeled benchmark are utilized for extensive experiments, showing improvement over both CNNs and VITs.

Joint Dense Residual and Recurrent Attention Network for DCE-MRI Breast Tumor Segmentation.

Breast cancer detection largely relies on imaging characteristics and the ability of clinicians to easily and quickly identify potential lesions. Magnetic resonance imaging (MRI) of breast tumors has recently shown great promise for enabling the automatic identification of breast tumors. Nevertheless, state-of-the-art MRI-based algorithms utilizing deep learning techniques are still limited in their ability to accurately separate tumor and healthy tissue. Therefore, in the current work, we propose an automatic and accurate two-stage U-Net-based segmentation framework for breast tumor detection using dynamic contrast-enhanced MRI (DCE-MRI). This framework was evaluated using T2-weighted MRI data from 160 breast tumor cases, and its performance was compared with that of the standard U-Net model. In the first stage of the proposed framework, a refined U-Net model was utilized to automatically delineate a breast region of interest (ROI) from the surrounding healthy tissue. Importantly, this automatic segmentation step reduced the impact of the background chest tissue on breast tumors' identification. For the second stage, we employed an improved U-Net model that combined a dense residual module based on dilated convolution with a recurrent attention module. This model was used to accurately and automatically segment the tumor tissue from healthy tissue in the breast ROI derived in the previous step. Overall, compared to the U-Net model, the proposed technique exhibited increases in the Dice similarity coefficient, Jaccard similarity, positive predictive value, sensitivity, and Hausdorff distance of 3%, 3%, 3%, 2%, and 16.2, respectively. The proposed model may in the future aid in the clinical diagnosis of breast cancer lesions and help guide individualized patient treatment.

CT and MRI Medical Image Fusion Using Noise-Removal and Contrast Enhancement Scheme with Convolutional Neural Network.

Medical image fusion (MIF) has received painstaking attention due to its diverse medical applications in response to accurately diagnosing clinical images. Numerous MIF methods have been proposed to date, but the fused image suffers from poor contrast, non-uniform illumination, noise presence, and improper fusion strategies, resulting in an inadequate sparse representation of significant features. This paper proposes the morphological preprocessing method to address the non-uniform illumination and noise by the bottom-hat-top-hat strategy. Then, grey-principal component analysis (grey-PCA) is used to transform RGB images into gray images that can preserve detailed features. After that, the local shift-invariant shearlet transform (LSIST) method decomposes the images into the low-pass (LP) and high-pass (HP) sub-bands, efficiently restoring all significant characteristics in various scales and directions. The HP sub-bands are fed to two branches of the Siamese convolutional neural network (CNN) by process of feature detection, initial segmentation, and consistency verification to effectively capture smooth edges, and textures. While the LP sub-bands are fused by employing local energy fusion using the averaging and selection mode to restore the energy information. The proposed method is validated by subjective and objective quality assessments. The subjective evaluation is conducted by a user case study in which twelve field specialists verified the superiority of the proposed method based on precise details, image contrast, noise in the fused image, and no loss of information. The supremacy of the proposed method is further justified by obtaining 0.6836 to 0.8794, 0.5234 to 0.6710, and 3.8501 to 8.7937 gain for QFAB, CRR, and AG and noise reduction from 0.3397 to 0.1209 over other methods for objective parameters.

Adaptive current harmonics suppression strategy for grid-tie inverters.

Since the observed angle of a phase-locked loop (PLL) is relatively accurate even under distorted grid conditions, the mathematical model of the voltage errors caused by the switching modulation and the dead-time effect are derived as a function of the grid voltage angle in this paper. Based on the model analysis, an adaptive compensation algorithm is proposed to suppress the grid-side current harmonics in three-phase converters. The proposed algorithm fits the unmeasurable voltage errors by a truncated Fourier series expansion, and then takes it as an equivalent disturbance in the current control loop to achieve harmonic compensation. By the feed-forward compensation, the design and tuning of the controller parameters are simplified and separated from the dynamic performance. In addition, the controller can adapt to the grid frequency variation by updating the grid voltage angle with the PLL block. To reduce the computational burden, a simplified version of the proposed method is also presented. Simulation and experiment results show that the proposed methods can suppress the current harmonics and achieve better performance in terms of total harmonic distortion, strong robustness and insensitivity to the grid frequency variations, compared with the traditional PI control or repetitive control strategy.

[An endpoint-detection algorithm of surface electromyography insensitive to electrocardiogram interference].

Surface electromyography (sEMG) has been widely used in the study of clinical medicine, rehabilitation medicine, sports, etc., and its endpoints should be detected accurately before analyzing. However, endpoint detection is vulnerable to electrocardiogram (ECG) interference when the sEMG recorders are placed near the heart. In this paper, an endpoint-detection algorithm which is insensitive to ECG interference is proposed. In the algorithm, endpoints of sEMG are detected based on the short-time energy and short-time zero-crossing rates of sEMG. The thresholds of short-time energy and short-time zero-crossing rate are set according to the statistical difference of short-time zero-crossing rate between sEMG and ECG, and the statistical difference of short-time energy between sEMG and the background noise. Experiment results on the sEMG of rectus abdominis muscle demonstrate that the algorithm detects the endpoints of the sEMG with a high accuracy rate of 95.6%.

Segmentation of pulmonary nodules using adaptive local region energy with probability density function-based similarity distance and multi-features clustering.

BACKGROUND: Pulmonary nodules in computerized tomography (CT) images are potential manifestations of lung cancer. Segmentation of potential nodule objects is the first necessary and crucial step in computer-aided detection system of pulmonary nodules. The segmentation of various types of nodules, especially for ground-glass opacity (GGO) nodules and juxta-vascular nodules, present various challenges. The nodule with GGO characteristic possesses typical intensity inhomogeneity and weak edges, which is difficult to define the boundary; the juxta-vascular nodule is connected to a vessel, and they have very similar intensities. Traditional segmentation methods may result in the problems of boundary leakage and a small volume over-segmentation. This paper deals with the above mentioned problems. METHODS: A novel segmentation method for pulmonary nodules is proposed, which uses an adaptive local region energy model with probability density function (PDF)-based similarity distance and multi-features dynamic clustering refinement method. Our approach has several novel aspects: (1) in the proposed adaptive local region energy model, the local domain for local energy model is selected adaptively based on k-nearest-neighbour (KNN) estimate method, and measurable distances between probability density functions of multi-dimension features with high class separability are used to build the cost function. (2) A multi-features dynamic clustering method is used for the segmentation refinement of juxta-vascular nodules, which is based on the nodule segmentation using active contour model (ACM) with adaptive local region energy and vessel segmentation using flow direction feature (FDF)-based region growing method. (3) it handles various types of nodules under a united framework. RESULTS: The proposed method has been validated on a clinical dataset of 113 chest CT scans that contain 157 nodules determined by a ground truth reading process, and evaluating the algorithm on the provided data leads to an average Tanimoto/Jaccard error of 0.17, 0.20 and 0.24 for GGO, juxta-vascular and GGO juxta-vascular nodules, respectively. CONCLUSIONS: Experimental results show desirable performances of the proposed method. The proposed segmentation method outperforms the traditional methods.

Topology adaptive vessel network skeleton extraction with novel medialness measuring function.

Vessel tree skeleton extraction is widely applied in vascular structure segmentation, however, conventional approaches often suffer from the adjacent interferences and poor topological adaptability. To avoid these problems, a robust, topology adaptive tree-like structure skeleton extraction framework is proposed in this paper. Specifically, to avoid the adjacent interferences, a local message passing procedure called Gaussian affinity voting (GAV) is proposed to realize adaptive scale-growing of vessel voxels. Then the medialness measuring function (MMF) based on GAV, namely GAV-MMF, is constructed to extract medialness patterns robustly. In order to improve topological adaptability, a level-set graph embedded with GAV-MMF is employed to build initial curve skeletons without any user interaction. Furthermore, the GAV-MMF is embedded in stretching open active contours (SOAC) to drive the initial curves to the expected location, maintaining smoothness and continuity. In addition, to provide an accurate and smooth final skeleton tree topology, topological checks and skeleton network reconfiguration is proposed. The continuity and scalability of this method is validated experimentally on synthetic and clinical images for multi-scale vessels. Experimental results show that the proposed method achieves acceptable topological adaptability for skeleton extraction of vessel trees.

Fuzzy speed function based active contour model for segmentation of pulmonary nodules.

Pulmonary nodules are potential manifestation of lung cancer. Accurate segmentation of juxta-vascular nodules and ground glass opacity (GGO) nodules is an important and active area of research in medical image processing. At present, the classical active contour models (ACM) for segmentation of pulmonary nodules may cause the problem of boundary leakage. In order to solve the problem, a new fuzzy speed function-based active model for segmentation of pulmonary nodules is proposed in this paper. The fuzzy speed function incorporated into the ACM is calculated by the degree of membership based on intensity feature and local shape index. At the boundary of pulmonary nodules, the fuzzy speed function approaches zero and the evolution of the contour curve will stop, so the accurate segmentation of pulmonary nodules can be obtained. Experimental results on juxta-vascular nodules and GGO nodules show that the proposed ACM can achieve accurate segmentation.

Detection of pulmonary nodules in CT images based on fuzzy integrated active contour model and hybrid parametric mixture model.

The segmentation and detection of various types of nodules in a Computer-aided detection (CAD) system present various challenges, especially when (1) the nodule is connected to a vessel and they have very similar intensities; (2) the nodule with ground-glass opacity (GGO) characteristic possesses typical weak edges and intensity inhomogeneity, and hence it is difficult to define the boundaries. Traditional segmentation methods may cause problems of boundary leakage and "weak" local minima. This paper deals with the above mentioned problems. An improved detection method which combines a fuzzy integrated active contour model (FIACM)-based segmentation method, a segmentation refinement method based on Parametric Mixture Model (PMM) of juxta-vascular nodules, and a knowledge-based C-SVM (Cost-sensitive Support Vector Machines) classifier, is proposed for detecting various types of pulmonary nodules in computerized tomography (CT) images. Our approach has several novel aspects: (1) In the proposed FIACM model, edge and local region information is incorporated. The fuzzy energy is used as the motivation power for the evolution of the active contour. (2) A hybrid PMM Model of juxta-vascular nodules combining appearance and geometric information is constructed for segmentation refinement of juxta-vascular nodules. Experimental results of detection for pulmonary nodules show desirable performances of the proposed method.

[Detection of lung mini-nodules using multi-feature tracking].

How to accurately identify mini-nodules in a large amount of high resolution computed tomography (HRCT) images is always a significant and difficult issue in lung nodule computer-aided detection (CAD). This paper describes a new mini-nodules detection method which is based on a multi-feature tracking algorithm. Our detection method began after running the Da-Jing algorithm and morphological operation to extract the lung region of every HRCT image in a sequence. Once the lung had been extracted, a hybrid algorithm, combining gray threshold and improved template matching, was used to obtain the regions of interest (ROD). Next, several characteristics of each ROI were calculated to identify the final results by using multi-feature tracking throughout the whole HRCT image sequence. The results showed that the proposed method would be of high accuracy with a low occurrence of false positives.

An optical model for translucent volume rendering and its implementation using the preintegrated shear-warp algorithm.

In order to efficiently and effectively reconstruct 3D medical images and clearly display the detailed information of inner structures and the inner hidden interfaces between different media, an Improved Volume Rendering Optical Model (IVROM) for medical translucent volume rendering and its implementation using the preintegrated Shear-Warp Volume Rendering algorithm are proposed in this paper, which can be readily applied on a commodity PC. Based on the classical absorption and emission model, effects of volumetric shadows and direct and indirect scattering are also considered in the proposed model IVROM. Moreover, the implementation of the Improved Translucent Volume Rendering Method (ITVRM) integrating the IVROM model, Shear-Warp and preintegrated volume rendering algorithm is described, in which the aliasing and staircase effects resulting from under-sampling in Shear-Warp, are avoided by the preintegrated volume rendering technique. This study demonstrates the superiority of the proposed method.

[On evaluating the robot-based experimental system for biomechanical experiment of human knee].

This is a report on how we use the hybrid force-displacement control method to load the human knee and analyze the effect and value of our robot experimental system through the biomechanical experiments of total meniscal resection of human knee. The whole robot control system can load continuously on the specimens, thus overcoming the shortcomings of the traditional loading methods which can only load discretely. In the meantime, by using the robot-based testing system, the force (torque) of the specimens and the spatial position under the force can be measured in real-time, which overcomes the shortcomings caused by the separation of force (torque) measurement from displacement measurement and so greatly improves the measurement accuracy.

[CAD for identifying malignant lung nodules in early diagnosis: a survey].

It is of paramount importance for the diagnosis and therapy of lung cancer, even for the increasing of 5-year survival rate in that the early dignosis of malignant pulmonary nodules are made by intelligent identification successfully. As it stands, in intelligent identification of pulmonary nodules, computer-aided detection/diagnosis (CAD) plays the most important role. The key points of intelligent identification of pulmonary nodules are (1) Detecting pulmonary nodules based on the characterization of nodule appearance; (2) Measuring accurately the nodule size; (3) Computing accurately the growth rate. This article presents a review on the basic technologies and methods of CAD for identifying malignant pulmonary nodules in the course of making early diagnosis, including lung segmentation, registration of volume data, identification of benign/malignant pulmonary nodule, and so on.

[A preliminary research on multi-source medical image fusion].

Multi-modal medical image fusion has important value in clinical diagnosis and treatment. In this paper, the multi-resolution analysis of Daubechies 9/7 Biorthogonal Wavelet Transform is introduced for anatomical and functional image fusion, then a new fusion algorithm with the combination of local standard deviation and energy as texture measurement is presented. At last, a set of quantitative evaluation criteria is given. Experiments show that both anatomical and metabolism information can be obtained effectively, and both the edge and texture features can be reserved successfully. The presented algorithm is more effective than the traditional algorithms.

[Research of joint-robotics-based design of biomechanics testing device on human spine].

This paper introduces the hardware and software of a biomechanical robot-based testing device. The bottom control orders, posture and torque data transmission, and the control algorithms are integrated in a unified visual control platform by Visual C+ +, with easy control and management. By using hybrid force-displacement control method to load the human spine, we can test the organizational structure and the force state of the FSU (Functional spinal unit) well, which overcomes the shortcomings due to the separation of the force and displacement measurement, thus greatly improves the measurement accuracy. Also it is esay to identify the spinal degeneration and the load-bearing impact on the organizational structure of the FSU after various types of surgery.

[Fast multi-resolution volume rendering method of large medical data sets].

A Fast Multi-resolution Volume Rendering Method (FMVRM) based on wavelet and Shear-Warp is herein proposed. In this method, the medical volume data is compressed using wavelet transformation first. Then based on the set resolution, the medical volume data is decompressed guided by Opacity transfer function (OTF). Finally, the 3D medical image is reconstructed on the basis of Shear-Warp using Block-based run length encoded (BRLE) data structure, in which, the aliasing artifacts resulting from under-sampling in Shear-Warp is avoided by the pre-integrated volume rendering technology. Experiments demonstrate the good performance of the proposed method.

[A hybrid volume rendering method using general hardware].

In order to improve the effect and efficiency of the reconstructed image after hybrid volume rendering of different kinds of volume data from medical sequential slices or polygonal models, we propose a hybrid volume rendering method based on Shear-Warp with economical hardware. First, the hybrid volume data are pre-processed by Z-Buffer method and RLE (Run-Length Encoded) data structure. Then, during the process of compositing intermediate image, a resampling method based on the dual-interpolation and the intermediate slice interpolation methods is used to improve the efficiency and the effect. Finally, the reconstructed image is rendered by the texture-mapping technology of OpenGL. Experiments demonstrate the good performance of the proposed method.

[Application of GVF snake model in segmentation of whole body bone SPECT image].

Limited by the imaging principle of whole body bone SPECT image, the gray value of bladder area is quite high, which affects the image's brightness, contrast and readability. In the meantime, the similarity between bladder area and focus makes it difficult for some images to be segmented automatically. In this paper, an improved Snake model, GVF Snake, is adopted to automatically segment bladder area, preparing for further processing of whole body bone SPECT images.

[Segmentation of whole body bone SPECT image based on BP neural network].

In this paper, BP neural network is used to segment whole body bone SPECT image so that the lesion area can be recognized automatically. For the uncertain characteristics of SPECT images, it is hard to achieve good segmentation result if only the BP neural network is employed. Therefore, the segmentation process is divided into three steps: first, the optimal gray threshold segmentation method is employed for preprocessing, then BP neural network is used to roughly identify the lesions, and finally template match method and symmetry-removing program are adopted to delete the wrongly recognized areas.