Development and Validation of a Self-Aligning Knee Exoskeleton With Hip Rotation Capability.

The self-aligning capability of an exoskeleton is important to ensure wearing comfort, and the delicate motion ability of the exoskeleton is essential for motion assistance. Designing a self-aligning exoskeleton that offers improved wearing comfort and enhanced motion-assistance functions remains a challenge. This paper proposes a novel spatial self-aligning mechanism for a knee exoskeleton to enable simultaneous assistance in the flexion and extension (FE) of the knee joint and the internal and external rotation (IER) of the hip joint. Additionally, considering the misalignment of the human-robot joint axes, a kinematic model of the knee exoskeleton is established and analyzed to demonstrate the kinematic compatibility of the exoskeleton. Furthermore, a global torque manipulability (GTM) index is proposed to evaluate the effects of dimensional parameters on the exoskeleton's performance, and then the knee exoskeleton is optimized according to the GTM index. Finally, experiments are conducted to validate the performance of the proposed exoskeleton. The experimental results show that during knee FE and hip IER, the proposed exoskeleton exhibits lower interaction forces and torques than existing exoskeletons.

A Double-Hurdle Quantification Model for Freezing of Gait of Parkinson's Patients.

Freezing of gait (FOG) leads to an increased risk of falls and limited mobility in individuals with Parkinson's disease (PD). However, existing research ignores the fine-grained quantitative assessment of FOG severity. This paper provides a double-hurdle model that uses typical spatiotemporal gait features to quantify the FOG severity in patients with PD. Moreover, a novel multi-output random forest algorithm is used as one hurdle of the double-hurdle model, further enhancing the model's performance. We conduct six experiments on a public PD gait database. Results demonstrate that the designed random forest algorithm in the double-hurdle model-hyperparameter independence framework achieves outstanding performances with the highest correlation coefficient (CC) of 0.972 and the lowest root mean square error (RMSE) of 2.488. Furthermore, we study the effect of drug state on the gait patterns of PD patients with or without FOG. Results show that "OFF" state amplifies the visibility of FOG symptoms in PD patients. Therefore, this study holds significant implications for the management and treatment of PD.

A Multi-Modal Classification Method for Early Diagnosis of Mild Cognitive Impairment and Alzheimer's Disease Using Three Paradigms With Various Task Difficulties.

Alzheimer's Disease (AD) accounts for the majority of dementia, and Mild Cognitive Impairment (MCI) is the early stage of AD. Early and accurate diagnosis of dementia plays a vital role in more targeted treatments and effectively halting disease progression. However, the clinical diagnosis of dementia requires various examinations, which are expensive and require a high level of expertise from the doctor. In this paper, we proposed a classification method based on multi-modal data including Electroencephalogram (EEG), eye tracking and behavioral data for early diagnosis of AD and MCI. Paradigms with various task difficulties were used to identify different severity of dementia: eye movement task and resting-state EEG tasks were used to detect AD, while eye movement task and delayed match-to-sample task were used to detect MCI. Besides, the effects of different features were compared and suitable EEG channels were selected for the detection. Furthermore, we proposed a data augmentation method to enlarge the dataset, designed an extra ERPNet feature extract layer to extract multi-modal features and used domain-adversarial neural network to improve the performance of MCI diagnosis. We achieved an average accuracy of 88.81% for MCI diagnosis and 100% for AD diagnosis. The results of this paper suggest that our classification method can provide a feasible and affordable way to diagnose dementia.

Design, Optimization, and Modeling of a Hydraulic Soft Robot for Chronic Total Occlusions.

Chronic total occlusion (CTO) is one of the most severe and sophisticated vascular stenosis because of complete blockage, greater operation difficulty, and lower procedural success rate. This study proposes a hydraulic-driven soft robot imitating the earthworm's locomotion to assist doctors or operators in actively opening thrombi in coronary or peripheral artery vessels. Firstly, a three-actuator bionic soft robot is developed based on earthworms' physiological structure. The soft robot's locomotion gait inspired by the earthworm's mechanism is designed. Secondly, the influence of structure parameters on actuator deformation, stress, and strain is explored, which can help us determine the soft actuators' optimal structure parameters. Thirdly, the relationship between hydraulic pressure and actuator deformation is investigated by performing finite element analysis using the bidirectional fluid-structure interaction (FSI) method. The kinematic models of the soft actuators are established to provide a valuable reference for the soft actuators' motion control.

EEG-Based Focus of Attention Tracking and Regulation During Dual-Task Training for Neural Rehabilitation of Stroke Patients.

Dual-task training under variable-priority instructions (DT-VP), during which subjects are required to vary their focus of attention (FOA) between two concurrent tasks, has shown a more significant improvement in neural rehabilitation than that under fixed-priority instructions. Failed FOA switching not only diminishes the recovery benefits, but also causes anxieties, which is detrimental to rehabilitation. Developing a strategy for tracking and regulating patients' FOA to achieve a better performance in task priority-following during DT-VP is thus imperative. In this study, fifteen stroke patients participated in DT-VP that comprised two tasks: a mathematical problem-solving task and a cycling task, during which their electroencephalograms were recorded simultaneously. The significantly differentiated power spectra of four brain regions extracted from single-task training were fed into a support vector machine to build a FOA tracking algorithm for patients' attention assessment during the DT-VP. Moreover, dual-task difficulty adaptation method was designed to regulate patients' FOA when their FOA and the high-priority task were not coincident. The comparison experimental results showed that the proposed method significantly improved patients' FOA distributed on the high-priority task (analysis of variance, 0.05). Meanwhile, the absolute power spectral densities of the motor cortex and the frontal region could also be improved during DT-VP under high motor and cognitive task priority instructions, respectively. These phenomena demonstrated the feasibility of the proposed method in helping stroke patients better implement FOA switching and maintenance.

Practical Predefined-Time Output-Feedback Consensus Tracking Control for Multiagent Systems.

This article addresses the issue of output-feedback consensus control of multiagent systems under the directed topology and subject to bounded external disturbances. By employing a smooth time-varying function, a distributed practical predefined-time (PPT) observer is developed to estimate the reference trajectory for the entire team (i.e., the leader's state) and a practical preset-time extended-state observer is also proposed to estimate bounded disturbances and unmeasurable system states. Next, a novel continuous and nonsingular PPT consensus control law is designed on the basis of the observers. Furthermore, the designed control protocol can achieve PPT stability, that is, consensus tracking errors are enforced to a neighborhood around zero within a predetermined time, which can be specified a priori, independent of initial states of agents and/or any other design parameters. Finally, illustrative numerical examples, including a comparative one, are provided to demonstrate the performance of the present predefined-time control approach.

A learnable EEG channel selection method for MI-BCI using efficient channel attention.

Introduction: During electroencephalography (EEG)-based motor imagery-brain-computer interfaces (MI-BCIs) task, a large number of electrodes are commonly used, and consume much computational resources. Therefore, channel selection is crucial while ensuring classification accuracy. Methods: This paper proposes a channel selection method by integrating the efficient channel attention (ECA) module with a convolutional neural network (CNN). During model training process, the ECA module automatically assigns the channel weights by evaluating the relative importance for BCI classification accuracy of every channel. Then a ranking of EEG channel importance can be established so as to select an appropriate number of channels to form a channel subset from the ranking. In this paper, the ECA module is embedded into a commonly used network for MI, and comparative experiments are conducted on the BCI Competition IV dataset 2a. Results and discussion: The proposed method achieved an average accuracy of 75.76% with all 22 channels and 69.52% with eight channels in a four-class classification task, outperforming other state-of-the-art EEG channel selection methods. The result demonstrates that the proposed method provides an effective channel selection approach for EEG-based MI-BCI.

High-resolution feature based central venous catheter tip detection network in X-ray images.

Hospital patients can have catheters and lines inserted during the course of their admission to give medicines for the treatment of medical issues, especially the central venous catheter (CVC). However, malposition of CVC will lead to many complications, even death. Clinicians always detect the malposition based on position detection of CVC tip via X-ray images. To reduce the workload of the clinicians and the percentage of malposition occurrence, we propose an automatic catheter tip detection framework based on a convolutional neural network (CNN). The proposed framework contains three essential components which are modified HRNet, segmentation supervision module, and deconvolution module. The modified HRNet can retain high-resolution features from start to end, ensuring the maintenance of precise information from the X-ray images. The segmentation supervision module can alleviate the presence of other line-like structures such as the skeleton as well as other tubes and catheters used for treatment. In addition, the deconvolution module can further increase the feature resolution on the top of the highest-resolution feature maps in the modified HRNet to get a higher-resolution heatmap of the catheter tip. A public CVC Dataset is utilized to evaluate the performance of the proposed framework. The results show that the proposed algorithm offering a mean Pixel Error of 4.11 outperforms three comparative methods (Ma's method, SRPE method, and LCM method). It is demonstrated to be a promising solution to precisely detect the tip position of the catheter in X-ray images.

Transformer Based Cross-Subject Mental Workload Classification Using FNIRS for Real-World Application.

Mental state monitoring is a hot topic especially in neurorehabilitation, skill training, etc, for which the functional near-infrared spectroscopy (fNIRS) has been suggested to be used, and fewer detection channels and cross-subject performance are usually required for real-world application. To this goal, we propose a transformer-based method for cross-subject mental workload classification using fewer channels of fNIRS. Firstly, the input fNIRS signals in a window are divided into patches in the temporal order and transformed into embeddings, to which a classification token and learnable position embeddings are added. Then, a transformer encoder is used to learn the long-range dependencies among the embeddings, of which the output classification token is sent to a multilayer perceptron (MLP) head. Mental workload classification results can be represented by the outputs of the MLP head. Finally, comparison experiments were conducted on the open-access fNIRS2MW dataset. The results show that, the proposed method can outperform previous methods in cross-subject classification accuracy, and relatively efficient computation can be obtained.

Graph Reasoning Module for Alzheimer's Disease Diagnosis: A Plug-and-Play Method.

Recent advances in deep learning have led to increased adoption of convolutional neural networks (CNN) for structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) detection. AD results in widespread damage to neurons in different brain regions and destroys their connections. However, current CNN-based methods struggle to relate spatially distant information effectively. To solve this problem, we propose a graph reasoning module (GRM), which can be directly incorporated into CNN-based AD detection models to simulate the underlying relationship between different brain regions and boost AD diagnosis performance. Specifically, in GRM, an adaptive graph Transformer (AGT) block is designed to adaptively construct a graph representation based on the feature map given by CNN, a graph convolutional network (GCN) block is adopted to update the graph representation, and a feature map reconstruction (FMR) block is built to convert the learned graph representation to a feature map. Experimental results demonstrate that the insertion of the GRM in the existing AD classification model can increase its balanced accuracy by more than 4.3%. The GRM-embedded model achieves state-of-the-art performance compared with current deep learning-based AD diagnosis methods, with a balanced accuracy of 86.2%.

Comparing Multi-Dimensional fNIRS Features Using Bayesian Optimization-Based Neural Networks for Mild Cognitive Impairment (MCI) Detection.

The diagnosis of mild cognitive impairment (MCI), a prodromal stage of Alzheimer's disease (AD), is essential for initiating timely treatment to delay the onset of AD. Previous studies have shown the potential of functional near-infrared spectroscopy (fNIRS) for diagnosing MCI. However, preprocessing fNIRS measurements requires extensive experience to identify poor-quality segments. Moreover, few studies have explored how proper multi-dimensional fNIRS features influence the classification results of the disease. Thus, this study outlined a streamlined fNIRS preprocessing method to process fNIRS measurements and compared multi-dimensional fNIRS features with neural networks in order to explore how temporal and spatial factors affect the classification of MCI and cognitive normality. More specifically, this study proposed using Bayesian optimization-based auto hyperparameter tuning neural networks to evaluate 1D channel-wise, 2D spatial, and 3D spatiotemporal features of fNIRS measurements for detecting MCI patients. The highest test accuracies of 70.83%, 76.92%, and 80.77% were achieved for 1D, 2D, and 3D features, respectively. Through extensive comparisons, the 3D time-point oxyhemoglobin feature was proven to be a more promising fNIRS feature for detecting MCI by using an fNIRS dataset of 127 participants. Furthermore, this study presented a potential approach for fNIRS data processing, and the designed models required no manual hyperparameter tuning, which promoted the general utilization of fNIRS modality with neural network-based classification to detect MCI.

Learning Skill Characteristics From Manipulations.

Percutaneous coronary intervention (PCI) has increasingly become the main treatment for coronary artery disease. The procedure requires high experienced skills and dexterous manipulations. However, there are few techniques to model PCI skill so far. In this study, a learning framework with local and ensemble learning is proposed to learn skill characteristics of different skill-level subjects from their PCI manipulations. Ten interventional cardiologists (four experts and six novices) were recruited to deliver a medical guidewire to two target arteries on a porcine model for in vivo studies. Simultaneously, translation and twist manipulations of thumb, forefinger, and wrist are acquired with electromagnetic (EM) and fiber-optic bend (FOB) sensors, respectively. These behavior data are then processed with wavelet packet decomposition (WPD) under 1-10 levels for feature extraction. The feature vectors are further fed into three candidate individual classifiers in the local learning layer. Furthermore, the local learning results from different manipulation behaviors are fused in the ensemble learning layer with three rule-based ensemble learning algorithms. In subject-dependent skill characteristics learning, the ensemble learning can achieve 100% accuracy, significantly outperforming the best local result (90%). Furthermore, ensemble learning can also maintain 73% accuracy in subject-independent schemes. These promising results demonstrate the great potential of the proposed method to facilitate skill learning in surgical robotics and skill assessment in clinical practice.

A Novel Spatial Position Prediction Navigation System Makes Surgery More Accurate.

During intravascular interventional surgery, the 3D surgical navigation system can provide doctors with 3D spatial information of the vascular lumen, reducing the impact of missing dimension caused by digital subtraction angiography (DSA) guidance and further improving the success rate of surgeries. Nevertheless, this task often comes with the challenge of complex registration problems due to vessel deformation caused by respiratory motion and high requirements for the surgical environment because of the dependence on external electromagnetic sensors. This article proposes a novel 3D spatial predictive positioning navigation (SPPN) technique to predict the real-time tip position of surgical instruments. In the first stage, we propose a trajectory prediction algorithm integrated with instrumental morphological constraints to generate the initial trajectory. Then, a novel hybrid physical model is designed to estimate the trajectory's energy and mechanics. In the second stage, a point cloud clustering algorithm applies multi-information fusion to generate the maximum probability endpoint cloud. Then, an energy-weighted probability density function is introduced using statistical analysis to achieve the prediction of the 3D spatial location of instrument endpoints. Extensive experiments are conducted on 3D-printed human artery and vein models based on a high-precision electromagnetic tracking system. Experimental results demonstrate the outstanding performance of our method, reaching 98.2% of the achievement ratio and less than 3 mm of the average positioning accuracy. This work is the first 3D surgical navigation algorithm that entirely relies on vascular interventional robot sensors, effectively improving the accuracy of interventional surgery and making it more accessible for primary surgeons.

Adaptive Fuzzy Asymptotic Tracking Control of State-Constrained High-Order Nonlinear Time-Delay Systems and Its Applications.

This article discusses the adaptive fuzzy asymptotic tracking control for high-order nonlinear time-delay systems with full-state constraints. Fuzzy-logic systems and a separation principle are utilized to relax growth assumptions imposed on unknown nonlinearities. The adverse effect caused by unknown time delays is eliminated by choosing appropriate Lyapunov-Krasovskii functionals. By integrating nonlinear-transformed functions with a key coordinate transformation into the control design and constructing a specific compact set on the initial values of system states, the desired trajectory and parameter estimates, it is rigorously proved that all closed-loop signals are semiglobally bounded, the fuzzy approximation is valid, the full-state constraints are not violated without feasibility conditions on virtual controllers, and asymptotic tracking is achieved. The effectiveness and advantages of this control scheme are confirmed by two examples including a single-link robotic system.

Removing Feasibility Conditions on Adaptive Neural Tracking Control of Nonlinear Time-Delay Systems With Time-Varying Powers, Input, and Full-State Constraints.

This article investigates the tracking control for input and full-state-constrained nonlinear time-delay systems with unknown time-varying powers, whose nonlinearities do not impose any growth assumption. By utilizing the auxiliary control signal and nonlinear state-dependent transformation (NSDT) to counteract the effect of input saturation and cope with full-state constraints, respectively, and then introducing lower and higher powers and Lyapunov-Krasovskii (L-K) functionals in control design together with the adaptive neural-networks (NNs) method, an adaptive neural tracking control design is provided without feasibility conditions. It is proved that NNs approximation is valid, all the closed-loop signals are semiglobally bounded, and input and full-state constraints are not violated.

Further Results on Adaptive Practical Tracking for High-Order Nonlinear Systems With Full-State Constraints.

In this article, an adaptive practical tracking control scheme is presented for full-state constrained high-order nonlinear systems. By skillfully introducing the adaptive gain, nonlinear transformed functions and sign functions into control design, a novel continuous state-feedback controller is constructed without imposing restrictive approximation techniques and feasibility conditions. Under mild assumptions, the boundedness of all the closed-loop signals can be guaranteed, full-state constraints are not transgressed for all time, and the tracking error tends to an arbitrarily small region of zero in a finite time.

Adversarial Binary Mutual Learning for Semi-Supervised Deep Hashing.

Hashing is a popular search algorithm for its compact binary representation and efficient Hamming distance calculation. Benefited from the advance of deep learning, deep hashing methods have achieved promising performance. However, those methods usually learn with expensive labeled data but fail to utilize unlabeled data. Furthermore, the traditional pairwise loss used by those methods cannot explicitly force similar/dissimilar pairs to small/large distances. Both weaknesses limit existing methods' performance. To solve the first problem, we propose a novel semi-supervised deep hashing model named adversarial binary mutual learning (ABML). Specifically, our ABML consists of a generative model GH and a discriminative model DH , where DH learns labeled data in a supervised way and GH learns unlabeled data by synthesizing real images. We adopt an adversarial learning (AL) strategy to transfer the knowledge of unlabeled data to DH by making GH and DH mutually learn from each other. To solve the second problem, we propose a novel Weibull cross-entropy loss (WCE) by using the Weibull distribution, which can distinguish tiny differences of distances and explicitly force similar/dissimilar distances as small/large as possible. Thus, the learned features are more discriminative. Finally, by incorporating ABML with WCE loss, our model can acquire more semantic and discriminative features. Extensive experiments on four common data sets (CIFAR-10, large database of handwritten digits (MNIST), ImageNet-10, and NUS-WIDE) and a large-scale data set ImageNet demonstrate that our approach successfully overcomes the two difficulties above and significantly outperforms state-of-the-art hashing methods.

Space Squeeze Reasoning and Low-Rank Bilinear Feature Fusion for Surgical Image Segmentation.

Surgical image segmentation is critical for surgical robot control and computer-assisted surgery. In the surgical scene, the local features of objects are highly similar, and the illumination interference is strong, which makes surgical image segmentation challenging. To address the above issues, a bilinear squeeze reasoning network is proposed for surgical image segmentation. In it, the space squeeze reasoning module is proposed, which adopts height pooling and width pooling to squeeze global contexts in the vertical and horizontal directions, respectively. The similarity between each horizontal position and each vertical position is calculated to encode long-range semantic dependencies and establish the affinity matrix. The feature maps are also squeezed from both the vertical and horizontal directions to model channel relations. Guided by channel relations, the affinity matrix is expanded to the same size as the input features. It captures long-range semantic dependencies from different directions, helping address the local similarity issue. Besides, a low-rank bilinear fusion module is proposed to enhance the model's ability to recognize similar features. This module is based on the low-rank bilinear model to capture the inter-layer feature relations. It integrates the location details from low-level features and semantic information from high-level features. Various semantics can be represented more accurately, which effectively improves feature representation. The proposed network achieves state-of-the-art performance on cataract image segmentation dataset CataSeg and robotic image segmentation dataset EndoVis 2018.

SurgiNet: Pyramid Attention Aggregation and Class-wise Self-Distillation for Surgical Instrument Segmentation.

Surgical instrument segmentation plays a promising role in robot-assisted surgery. However, illumination issues often appear in surgical scenes, altering the color and texture of surgical instruments. Changes in visual features make surgical instrument segmentation difficult. To address illumination issues, the SurgiNet is proposed to learn pyramid attention features. The double attention module is designed to capture the semantic dependencies between locations and channels. Based on semantic dependencies, the semantic features in the disturbed area can be inferred for addressing illumination issues. Pyramid attention is aggregated to capture multi-scale features and make predictions more accurate. To perform model compression, class-wise self-distillation is proposed to enhance the representation learning of the network, which performs feature distillation within the class to eliminate interference from other classes. Top-down and multi-stage knowledge distillation is designed to distill class probability maps. By inter-layer supervision, high-level probability maps are applied to calibrate the probability distribution of low-level probability maps. Since class-wise distillation enhances the self-learning of the network, the network can get excellent performance with a lightweight backbone. The proposed network achieves the state-of-the-art performance of 89.14% mIoU on CataIS with only 1.66 GFlops and 2.05 M parameters. It also takes first place on EndoVis 2017 with 66.30% mIoU.

TR-GAN: Multi-Session Future MRI Prediction With Temporal Recurrent Generative Adversarial Network.

Magnetic Resonance Imaging (MRI) has been proven to be an efficient way to diagnose Alzheimer's disease (AD). Recent dramatic progress on deep learning greatly promotes the MRI analysis based on data-driven CNN methods using a large-scale longitudinal MRI dataset. However, most of the existing MRI datasets are fragmented due to unexpected quits of volunteers. To tackle this problem, we propose a novel Temporal Recurrent Generative Adversarial Network (TR-GAN) to complete missing sessions of MRI datasets. Unlike existing GAN-based methods, which either fail to generate future sessions or only generate fixed-length sessions, TR-GAN takes all past sessions to recurrently and smoothly generate future ones with variant length. Specifically, TR-GAN adopts recurrent connection to deal with variant input sequence length and flexibly generate future variant sessions. Besides, we also design a multiple scale & location (MSL) module and a SWAP module to encourage the model to better focus on detailed information, which helps to generate high-quality MRI data. Compared with other popular GAN architectures, TR-GAN achieved the best performance in all evaluation metrics of two datasets. After expanding the Whole MRI dataset, the balanced accuracy of AD vs. cognitively normal (CN) vs. mild cognitive impairment (MCI) and stable MCI vs. progressive MCI classification can be increased by 3.61% and 4.00%, respectively.