Sagittal balance parameters measurement on cervical spine MR images based on superpixel segmentation.

Introduction: Magnetic Resonance Imaging (MRI) is essential in diagnosing cervical spondylosis, providing detailed visualization of osseous and soft tissue structures in the cervical spine. However, manual measurements hinder the assessment of cervical spine sagittal balance, leading to time-consuming and error-prone processes. This study presents the Pyramid DBSCAN Simple Linear Iterative Cluster (PDB-SLIC), an automated segmentation algorithm for vertebral bodies in T2-weighted MR images, aiming to streamline sagittal balance assessment for spinal surgeons. Method: PDB-SLIC combines the SLIC superpixel segmentation algorithm with DBSCAN clustering and underwent rigorous testing using an extensive dataset of T2-weighted mid-sagittal MR images from 4,258 patients across ten hospitals in China. The efficacy of PDB-SLIC was compared against other algorithms and networks in terms of superpixel segmentation quality and vertebral body segmentation accuracy. Validation included a comparative analysis of manual and automated measurements of cervical sagittal parameters and scrutiny of PDB-SLIC's measurement stability across diverse hospital settings and MR scanning machines. Result: PDB-SLIC outperforms other algorithms in vertebral body segmentation quality, with high accuracy, recall, and Jaccard index. Minimal error deviation was observed compared to manual measurements, with correlation coefficients exceeding 95%. PDB-SLIC demonstrated commendable performance in processing cervical spine T2-weighted MR images from various hospital settings, MRI machines, and patient demographics. Discussion: The PDB-SLIC algorithm emerges as an accurate, objective, and efficient tool for evaluating cervical spine sagittal balance, providing valuable assistance to spinal surgeons in preoperative assessment, surgical strategy formulation, and prognostic inference. Additionally, it facilitates comprehensive measurement of sagittal balance parameters across diverse patient cohorts, contributing to the establishment of normative standards for cervical spine MR imaging.

Multimodal Sensors Enabled Autonomous Soft Robotic System with Self-Adaptive Manipulation.

Human hands are amazingly skilled at recognizing and handling objects of different sizes and shapes. To date, soft robots rarely demonstrate autonomy equivalent to that of humans for fine perception and dexterous operation. Here, an intelligent soft robotic system with autonomous operation and multimodal perception ability is developed by integrating capacitive sensors with triboelectric sensor. With distributed multiple sensors, our robot system can not only sense and memorize multimodal information but also enable an adaptive grasping method for robotic positioning and grasp control, during which the multimodal sensory information can be captured sensitively and fused at feature level for crossmodally recognizing objects, leading to a highly enhanced recognition capability. The proposed system, combining the performance and physical intelligence of biological systems (i.e., self-adaptive behavior and multimodal perception), will greatly advance the integration of soft actuators and robotics in many fields.

Modular Soft Robot with Origami Skin for Versatile Applications.

Recent advances in soft robotics demonstrate the requirement of modular actuation to enable the rapid replacement of actuators for maintenance and functionality extension. There remain challenges to designing soft actuators capable of different motions with a consistent appearance for simplifying fabrication and modular connection. Origami structures reshaping along with their unique creases became a powerful tool to provide compact constraint layers for soft pneumatic actuators. Inspired by Waterbomb and Kresling origami, this article presents three types of vacuum-driven soft actuators with a cubic shape and different origami skins, featuring contraction, bending, and twisting-contraction combined motions, respectively. In addition, these modular actuators with diversified motion patterns can be directly fabricated by molding silicone shell and constraint layers together. Actuators with different geometrical parameters are characterized to optimize the structure and maximize output properties after establishing a theoretical model to predict the deformation. Owing to the shape consistency, our actuators can be further modularized to achieve modular actuation via mortise and tenon-based structures, promoting the possibility and efficiency of module connection for versatile tasks. Eventually, several types of modular soft robots are created to achieve fragile object manipulation and locomotion in various environments to show their potential applications.

Stiffness-Tunable Soft Gripper with Soft-Rigid Hybrid Actuation for Versatile Manipulations.

Highly flexible and environmentally adaptive soft robots have received considerable attention. There remains a demand for soft robots to realize the stiffness modulation and variable workspace for robust and versatile manipulations. This article presents a compact soft gripper with a polylactic acid-based variable stiffness module (VSM) and a rigid retractable mechanism to achieve soft-rigid hybrid actuation. The soft gripper can enhance its stiffness by 18-fold without sacrificing flexibility due to the VSM. A heating circuit is designed to divide the VSM into three regions. Each region can be activated separately for varying flexible segments to amplify the dexterity. Meanwhile, the water-cooling system accelerates the heat exchange, thus reducing the cooling time from ∼400 to 39 s. The rigid retractable mechanism can adjust the initial layout of the gripper to expand the workspace and perform manipulation by opening and closing fingers. The soft finger combined with stiffness tunability can maintain its deformation after being stiffened to realize morphing. Therefore, it can efficiently perform a grasp with a high load and avoid repeated heating and cooling, especially for items with a similar shape. The performance of the gripper is further validated by measuring the grasping force and grasping demonstration with various objects, showing its robustness and dexterity in versatile tasks.

Deep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI.

To help doctors and patients evaluate lumbar intervertebral disc degeneration (IVDD) accurately and efficiently, we propose a segmentation network and a quantitation method for IVDD from T2MRI. A semantic segmentation network (BianqueNet) composed of three innovative modules achieves high-precision segmentation of IVDD-related regions. A quantitative method is used to calculate the signal intensity and geometric features of IVDD. Manual measurements have excellent agreement with automatic calculations, but the latter have better repeatability and efficiency. We investigate the relationship between IVDD parameters and demographic information (age, gender, position and IVDD grade) in a large population. Considering these parameters present strong correlation with IVDD grade, we establish a quantitative criterion for IVDD. This fully automated quantitation system for IVDD may provide more precise information for clinical practice, clinical trials, and mechanism investigation. It also would increase the number of patients that can be monitored.

Wearable Triboelectric Sensors Enabled Gait Analysis and Waist Motion Capture for IoT-Based Smart Healthcare Applications.

Gait and waist motions always contain massive personnel information and it is feasible to extract these data via wearable electronics for identification and healthcare based on the Internet of Things (IoT). There also remains a demand to develop a cost-effective human-machine interface to enhance the immersion during the long-term rehabilitation. Meanwhile, triboelectric nanogenerator (TENG) revealing its merits in both wearable electronics and IoT tends to be a possible solution. Herein, the authors present wearable TENG-based devices for gait analysis and waist motion capture to enhance the intelligence and performance of the lower-limb and waist rehabilitation. Four triboelectric sensors are equidistantly sewed onto a fabric belt to recognize the waist motion, enabling the real-time robotic manipulation and virtual game for immersion-enhanced waist training. The insole equipped with two TENG sensors is designed for walking status detection and a 98.4% identification accuracy for five different humans aiming at rehabilitation plan selection is achieved by leveraging machine learning technology to further analyze the signals. Through a lower-limb rehabilitation robot, the authors demonstrate that the sensory system performs well in user recognition, motion monitoring, as well as robot and gaming-aided training, showing its potential in IoT-based smart healthcare applications.

Triboelectric nanogenerator sensors for soft robotics aiming at digital twin applications.

Designing efficient sensors for soft robotics aiming at human machine interaction remains a challenge. Here, we report a smart soft-robotic gripper system based on triboelectric nanogenerator sensors to capture the continuous motion and tactile information for soft gripper. With the special distributed electrodes, the tactile sensor can perceive the contact position and area of external stimuli. The gear-based length sensor with a stretchable strip allows the continuous detection of elongation via the sequential contact of each tooth. The triboelectric sensory information collected during the operation of soft gripper is further trained by support vector machine algorithm to identify diverse objects with an accuracy of 98.1%. Demonstration of digital twin applications, which show the object identification and duplicate robotic manipulation in virtual environment according to the real-time operation of the soft-robotic gripper system, is successfully created for virtual assembly lines and unmanned warehouse applications.

Thermally Reduced Graphene Oxide/Carbon Nanotube Composite Films for Thermal Packaging Applications.

Thermally reduced graphene oxide/carbon nanotube (rGO/CNT) composite films were successfully prepared by a high-temperature annealing process. Their microstructure, thermal conductivity and mechanical properties were systematically studied at different annealing temperatures. As the annealing temperature increased, more oxygen-containing functional groups were removed from the composite film, and the percentage of graphene continuously increased. When the annealing temperature increased from 1100 to 1400 °C, the thermal conductivity of the composite film also continuously increased from 673.9 to 1052.1 W m-1 K-1. Additionally, the Young's modulus was reduced by 63.6%, and the tensile strength was increased by 81.7%. In addition, the introduction of carbon nanotubes provided through-plane thermal conduction pathways for the composite films, which was beneficial for the improvement of their through-plane thermal conductivity. Furthermore, CNTs apparently improved the mechanical properties of rGO/CNT composite films. Compared with the rGO film, 1 wt% CNTs reduced the Young's modulus by 93.3% and increased the tensile strength of the rGO/CNT composite film by 60.3%, which could greatly improve its flexibility. Therefore, the rGO/CNT composite films show great potential for application as thermal interface materials (TIMs) due to their high in-plane thermal conductivity and good mechanical properties.

Intensity-Assisted ICP for Fast Registration of 2D-LIDAR.

Iterative closest point (ICP) is a method commonly used to perform scan-matching and registration. To be a simple and robust algorithm, it is still computationally expensive, and it has been regarded as having a crucial challenge especially in a real-time application as used for the simultaneous localization and mapping (SLAM) problem. For these reasons, this paper presents a new method for the acceleration of ICP with an assisted intensity. Unlike the conventional ICP, this method is proposed to reduce the computational cost and avoid divergences. An initial transformation guess is computed with an assisted intensity for their relative rigid-body transformation. Moreover, a target function is proposed to determine the best initial transformation guess based on the statistic of their spatial distances and intensity residuals. Additionally, this method is also proposed to reduce the iteration number. The Anderson acceleration is utilized for increasing the iteration speed which has better ability than the Picard iteration procedure. The proposed algorithm is operated in real time with a single core central processing unit (CPU) thread. Hence, it is suitable for the robot which has limited computation resources. To validate the novelty, this proposed method is evaluated on the SEMANTIC3D.NET benchmark dataset. According to comparative results, the proposed method is declared as having better accuracy and robustness than the conventional ICP methods.

Research on Modeling and Analysis of Generative Conversational System Based on Optimal Joint Structural and Linguistic Model.

Generative conversational systems consisting of a neural network-based structural model and a linguistic model have always been considered to be an attractive area. However, conversational systems tend to generate single-turn responses with a lack of diversity and informativeness. For this reason, the conversational system method is further developed by modeling and analyzing the joint structural and linguistic model, as presented in the paper. Firstly, we establish a novel dual-encoder structural model based on the new Convolutional Neural Network architecture and strengthened attention with intention. It is able to effectively extract the features of variable-length sequences and then mine their deep semantic information. Secondly, a linguistic model combining the maximum mutual information with the foolish punishment mechanism is proposed. Thirdly, the conversational system for the joint structural and linguistic model is observed and discussed. Then, to validate the effectiveness of the proposed method, some different models are tested, evaluated and compared with respect to Response Coherence, Response Diversity, Length of Conversation and Human Evaluation. As these comparative results show, the proposed method is able to effectively improve the response quality of the generative conversational system.

Atomic Layer Deposition of Buffer Layers for the Growth of Vertically Aligned Carbon Nanotube Arrays.

Vertically aligned carbon nanotube arrays (VACNTs) show a great potential for various applications, such as thermal interface materials (TIMs). Besides the thermally oxidized SiO2, atomic layer deposition (ALD) was also used to synthesize oxide buffer layers before the deposition of the catalyst, such as Al2O3, TiO2, and ZnO. The growth of VACNTs was found to be largely dependent on different oxide buffer layers, which generally prevented the diffusion of the catalyst into the substrate. Among them, the thickest and densest VACNTs could be achieved on Al2O3, and carbon nanotubes were mostly triple-walled. Besides, the deposition temperature was critical to the growth of VACNTs on Al2O3, and their growth rate obviously reduced above 650 °C, which might be related to the Ostwald ripening of the catalyst nanoparticles or subsurface diffusion of the catalyst. Furthermore, the VACNTs/graphene composite film was prepared as the thermal interface material. The VACNTs and graphene were proved to be the effective vertical and transverse heat transfer pathways in it, respectively.

Chemical Vapor Deposition of Vertically Aligned Carbon Nanotube Arrays: Critical Effects of Oxide Buffer Layers.

Vertically aligned carbon nanotubes (VACNTs) were synthesized on different oxide buffer layers using chemical vapor deposition (CVD). The growth of the VACNTs was mainly determined by three factors: the Ostwald ripening of catalyst nanoparticles, subsurface diffusion of Fe, and their activation energy for nucleation and initial growth. The surface roughness of buffer layers largely influenced the diameter and density of catalyst nanoparticles after annealing, which apparently affected the lifetime of the nanoparticles and the thickness of the prepared VACNTs. In addition, the growth of the VACNTs was also affected by the deposition temperature, and the lifetime of the catalyst nanoparticles apparently decreased when the deposition temperature was greater than 600 °C due to their serious Ostwald ripening. Furthermore, in addition to the number of catalyst nanoparticles, the density of the VACNTs was also largely dependent on their activation energy for nucleation and initial growth.

Improved three-dimensional reconstruction algorithm from a multifocus microscopic image sequence based on a nonsubsampled wavelet transform.

In the multifocus microscopic image measurement method, the distortion of the three-dimensional (3D) reconstruction model has always been an important factor affecting the measurement result. In spatial domains, the focus measure algorithm is based on the gradient change of the pixel point to determine the degree of focus of the pixel. So it will be difficult to accurately extract the focus of the pixel in the areas where color difference is not obvious, resulting in 3D model distortion. According to the optical principle, the high-frequency coefficients of the clear image are larger than the high-frequency coefficients of the blurred image. Based on this characteristic, this paper proposes a new multifocus microscopic image 3D reconstruction algorithm using a nonsubsampled wavelet transform (NSWT). The NSWT does not consider the downsampling in wavelet decomposition and has translational invariance. Therefore, the wavelet transform value of each pixel can be calculated in the image, so the high-frequency coefficient of each pixel can be obtained; then the convolution calculation is performed on the high-frequency coefficients of the pixel points in the fixed window as the focus measure value of the pixel point. Compared with the traditional algorithm, the algorithm proposed in this paper can show better unimodal and antinoise performance on the focusing measure curve. In this paper, the reconstruction of the experimental object is Alicona standard block triangular and semicylindrical. The proposed algorithm and the traditional algorithm for comprehensive measure use the root mean square error, peak signal to noise ratio, and correlation coefficient as the measure index. The experimental results and comparative analysis prove the correctness of the proposed algorithm and enable more accurate reconstruction of 3D models based on multifocus microscopic images.

Three-dimensional surface microtopography recovery from a multifocus image sequence using an omnidirectional modified Laplacian operator with adaptive window size.

Optical microscopy enables the observation of highly magnified objects and material structures on microsurfaces, but it can only acquire 2D images. In order to observe areal features more accurately and intuitively, 3D surface microtopography recovery has been applied to form a 3D surface model of an object from its 2D image sequence. In the 3D reconstruction of the focus evaluation operator, we have the gray variance operator, the gray-scale difference absolute sum operator, the Roberts gradient operator, the Tenengrad gradient operator, the improved Laplace operator, etc. There are two problems with these operators: one is that there is no difference between (x,y) and the gray scale of the pixel in the diagonal direction in the field and the other is that the window size of the focus evaluation operator is fixed, e.g., 3×3, 5×5, etc. Thus, the size of the window for each pixel in the image is the same, and the small window may not cover enough field information while being vulnerable to noise. Large windows can cover more information, but they may result in a smoothing phenomenon, which affects the accuracy of the model. Different pixels around the field have different pixel colors when the size of the window is not the same. Therefore, this paper proposes a modified omnidirectional Laplacian operator with an adaptive window to automatically adjust the size of the window according to the color difference within the window. This also takes into consideration the pixels in the diagonal direction. In addition, very comprehensive verification experiments proved the conclusions.