Biomedical Engineering Letters最新文献

This paper demonstrates real-time, label-free, contact-based glucose sensor design of inset-fed Microstrip Patch Antenna (MSPA) genres: Slotted Microstrip Patch Antenna (SMSPA) and Through-hole Microstrip Patch Antenna (THMSPA). In SMSPA, multiple slots are created along the width edge of the patch. In THMSPA, a through-hole is introduced across the antenna including all the layers: patch, substrate and ground conductor of the MSPA. The proposed designs are geared towards enhancing the electric field distribution along the patch, and to utilize that region as the sensing area. The electric field intensity at the resonant frequency is 45505V/m, 53145V/m and 71348V/m for MSPA, SMSPA and THMSPA, respectively. Experimental sensitivity of the proposed glucose sensor increased from 8.901dB/g/ml to 23.575dB/g/ml and 41.525dB/g/ml for SMSPA and THMSPA, respectively. There is significant enhancement in sensitivity in terms of MHz/g/ml for MSPA, SMSPA and THMSPA which is 112.286, 174.857 and 548.571, respectively.

Background: NAFLD is gaining recognition as a complex, multifactorial condition with suspected associations with endocrine disorders. This investigation employed MR analysis to explore the potential causality linking NAFLD to a spectrum of endocrine diseases, encompassing T1D, T2D, obesity, graves' disease, and acromegaly.

Methods: Our methodology leveraged a stringent IV selection process, adhering to the STROBE-MR guidelines. The MR analysis was conducted utilizing three distinct methods: IVW, WM, and MR-Egger. The IVW method was prioritized as the primary analytical approach. We conducted MR analyses to analyze the causal relationship between NAFLD and metabolic disorders. We also examined 1400 metabolites implicated in NAFLD. Metabolic pathway analysis was performed using the MetaboAnalyst database.

Results: The findings indicated that T2D (OR = 1.211, 95%CI: 0.836-1.585) and obesity (OR = 1.245, 95%CI: 0.816-1.674) are associated with an increased risk of NAFLD development. Further exploration into the the 1400 metabolites revealed that cys-gly and diacetylornithine are predictive of NAFLD, T2D, and obesity, whereas isovalerylcarnitine exhibited an inverse association, potentially inhibiting disease development. Metabolic pathways involving alanine, aspartate, and glutamate metabolism were identified as pivotal regulators in the pathophysiology of NAFLD, T2D, and obesity.

Conclusion: The present study generated innovative viewpoints on the etiology of NAFLD. Our findings underscore the significant role of T2D and obesity in NAFLD pathogenesis through metabolic pathways, presenting opportunities for targeted therapeutic strategies and warranting further investigation.

Supplementary information: The online version contains supplementary material available at 10.1007/s13534-024-00442-8.

Robotic systems rely on spatio-temporal information to solve control tasks. With advancements in deep neural networks, reinforcement learning has significantly enhanced the performance of control tasks by leveraging deep learning techniques. However, as deep neural networks grow in complexity, they consume more energy and introduce greater latency. This complexity hampers their application in robotic systems that require real-time data processing. To address this issue, spiking neural networks, which emulate the biological brain by transmitting spatio-temporal information through spikes, have been developed alongside neuromorphic hardware that supports their operation. This paper reviews brain-inspired learning rules and examines the application of spiking neural networks in control tasks. We begin by exploring the features and implementations of biologically plausible spike-timing-dependent plasticity. Subsequently, we investigate the integration of a global third factor with spike-timing-dependent plasticity and its utilization and enhancements in both theoretical and applied research. We also discuss a method for locally applying a third factor that sophisticatedly modifies each synaptic weight through weight-based backpropagation. Finally, we review studies utilizing these learning rules to solve control tasks using spiking neural networks.

Alzheimer's disease (AD) is a neurodegenerative disorder with an irreversible progression. Currently, it is diagnosed using invasive and costly methods, such as cerebrospinal fluid analysis, neuroimaging, and neuropsychological assessments. Recent studies indicate that certain changes in language ability can predict early cognitive decline, highlighting the potential of speech analysis in AD recognition. Based on this premise, this study proposes an AD recognition multi-channel network framework, which is referred to as the ADNet. It integrates both time-domain and frequency-domain features of speech signals, using waveform images and log-Mel spectrograms derived from raw speech as data sources. The framework employs inverted residual blocks to enhance the learning of low-level time-domain features and uses gated multi-information units to effectively combine local and global frequency-domain features. The study tests it on a dataset from the Shanghai cognitive screening (SCS) digital neuropsychological assessment. The results show that the method we proposed outperforms existing speech-based methods, achieving an accuracy of 88.57%, a precision of 88.67%, and a recall of 88.64%. This study demonstrates that the proposed framework can effectively distinguish between the AD and normal controls, and it may be useful for developing early recognition tools for AD.

Brain-computer interface (BCI) has been widely used in human-computer interaction. The introduction of artificial intelligence has further improved the performance of BCI system. In recent years, the development of BCI has gradually shifted from personal computers to embedded devices, which boasts lower power consumption and smaller size, but at the cost of limited device resources and computing speed, thus can hardly improve the support of complex algorithms. This paper proposes a heterogeneous BCI architecture based on ARM + FPGA, enabling real-time processing of electroencephalogram (EEG) signals. Adopting data quantization, layer fusion and data augmentation to optimize the compact neural network model EEGNet, and design dedicated hardware engines to accelerate the network. Experimental results show that the system achieves 93.3% classification accuracy for steady-state visual evoked potential signals, with a time delay of 0.2 ms per trail, and a power consumption of approximately (1.91 W). That is 31.5 times faster acceleration is realized at the cost of only 0.7% lower accuracy compared with the conventional processor. The results show that the BCI architecture proposed in this study has strong practicability and high research significance.

Stereotactic systems have traditionally used Cartesian coordinate combined with linear algebraic mathematical models to navigate the brain. Previously, the development of a novel stereotactic system allowed for improved patient comfort, reduced size, and carried through a simplified interface for surgeons. The system was designed with a work envelope and trajectory range optimized for deep brain stimulation applications only. However, it could be applied in multiple realms of neurosurgery by spanning the entire brain. To this end, a system of translational and rotational adapters was developed to allow total brain navigation capabilities. Adapters were designed to fit onto a Skull Anchor Key of a stereotactic frame system to allow for rotation and translation of the work envelope. Mathematical formulas for the rotations and translations associated with each adapter were developed. Mechanical and image-guided accuracies were examined using a ground truth imaging phantom. The system's clinical workflow and its ability to reliably and accurately be used in a surgical scenario were investigated using a cadaver head and computed tomography guidance. Eight adapters designed and 3D-printed allowed the work envelope to be expanded to the entire head. The mechanical error was 1.75 ± 0.09 mm (n = 20 targets), and the cadaver surgical targeting error was 1.18 ± 0.28 mm (n = 10 implantations). The novel application of conventional and geometric algebra in conjunction with hardware modifications significantly expands the work envelope of the stereotactic system to the entire cranial cavity. This approach greatly extends the clinical applications by the system.

A weight-bearing lateral radiograph (WBLR) of the foot is a gold standard for diagnosing adult-acquired flatfoot deformity. However, it is difficult to measure the major axis of bones in WBLR without using auxiliary lines. Herein, we develop semantic segmentation with a deep learning model (DLm) on the WBLR of the foot for enhanced diagnosis of pes planus and pes cavus. We used 300 consecutive WBLRs from young Korean males. The semantic segmentation model was developed based on U²-Net. An expert orthopedic surgeon manually labeled ground truths. We used 200 radiographs for training, 100 for internal validation, and two external datasets for external validation. The model was trained using a hybrid loss function, combining Dice Loss and boundary-based loss, to enhance both overall segmentation accuracy and precise delineation of boundary regions between pes planus and pes cavus. Angle measurement errors with minimum moment of inertia (MMI) and ellipsoidal fitting (EF) based on the segmentation results were evaluated. The DLm exhibited better results than human observers. For internal validation, the absolute angle errors of the DLm using MMI and EF were 0.92 ± 1.32° and 1.34 ± 2.07°, respectively. In external validation, these errors were 1.17 ± 1.60° and 1.60 ± 2.42° for AMC's dataset, and 1.23 ± 1.39° and 1.68 ± 1.98° for the LERA dataset, respectively. The DLm showed higher overall diagnostic accuracy than human observers in identifying flatfoot angles, regardless of the measurement methods. The absolute angle errors and diagnostic accuracy of the developed DLm are superior to those of the three human observers. Furthermore, when comparing the angle measurement methods within the DLm, the MMI method proves to be more accurate than EF. Finally, the proposed deep learning model, particularly with the implementation of the U²-Net demonstrates enhanced boundary segmentation and achieves sufficient external validation results, affirming its applicability in the real clinical setting.

Supplementary information: The online version contains supplementary material available at 10.1007/s13534-024-00439-3.

In recent years, robotic assistance has become increasingly used and applied in minimally invasive surgeries. A new cooperative surgical robot system that includes a joystick-guided robotic scope holder was developed in this study, and its feasibility for use in minimally invasive abdominal surgery was evaluated in a preclinical setting. The cooperative surgical robot consists of a six-degree-of-freedom collaborative robot arm and a one-degree-of-freedom bidirectional telescopic end-effector specializing in surgical assistance. The robot holds the endoscopic camera and performs remote center of motion based on the port into which the trocar is inserted. Surgeons can operate the robot with joysticks or hand-guided control. Cadaveric sessions were conducted in a male human cadaver to evaluate the system's potential to provide adequate surgical access and the reach required to complete a range of general abdominal surgeries. The results indicated that minimally invasive abdominal surgeries (low anterior resection, appendectomy, and cholecystectomy) were technically feasible with the new cooperative surgical robot, with docking times of 43, 26, and 32 s, respectively. The operative times were 15, 55, and 35 min for appendectomy, total mesorectal excision, and cholecystectomy, respectively. A National Aeronautics and Space Administration Task Load Index cognitive workload assessment by six surgeons who participated in the cadaveric study, resulted in an acceptable global score of 42.2. This preclinical study demonstrated that the new cooperative robotic surgery is usable in minimally invasive abdominal surgeries. Further simulations are necessary to confirm this promising product.

Parkinson's disease is a neurodegenerative disorder principally manifested as motor disabilities. In clinical practice, diagnostic rating scales are available for broadly measuring, classifying, and characterizing the disease progression. Nonetheless, these scales depend on the specialist's expertise, introducing a high degree of subjectivity. Thus, diagnosis and motor stage identification may be affected by misinterpretation, leading to incorrect or misguided treatments. This work addresses how to learn multimodal representations based on compact gait and eye motion descriptors whose fusion improves disease diagnosis prediction. This work introduces a noninvasive multimodal strategy that combines gait and ocular pursuit motion modalities into a geometrical Riemannian Neural Network for PD quantification and diagnostic support. Markerless gait and ocular pursuit videos were first recorded as Parkinson's observations, which are represented at each frame by a set of frame convolutional deep features. Then, Riemannian means are computed per modality using frame-level covariances coded from convolutional deep features. Thus, a geometrical learning representation is adjusted by Riemannian means, following early, intermediate, and late fusion alternatives. The adjusted Riemannian manifold combines input modalities to obtain PD prediction. The geometrical multimodal approach was validated in a study involving 13 control subjects and 19 PD patients, achieving a mean accuracy of 96% for early and intermediate fusion and 92% for late fusion, increasing the unimodal accuracy results obtained in the gait and eye movement modalities by 6 and 8%, respectively. The proposed method was able to discriminate Parkinson's patients from healthy subjects using multimodal geometrical configurations based on covariances descriptors. The covariance representation of video descriptors is highly compact (with an input size of 625 and an output size of 256 (1 BiRe)), facilitating efficient learning with a small number of samples, a crucial aspect in medical applications.

The limited imaging depth of optical endoscope restrains the identification of tissues under surface during the minimally invasive spine surgery (MISS), thus increasing the risk of critical tissue damage. This study is proposed to improve the accuracy and effectiveness of automatic spinal soft tissue identification using a forward-oriented ultrasound endoscopic system. Total 758 ex-vivo soft tissue samples were collected from ovine spines to create a dataset with four categories including spinal cord, nucleus pulposus, adipose tissue, and nerve root. Three conventional methods including Gray-level co-occurrence matrix (GLCM), Empirical Wavelet Transform (EWT), Variational Mode Decomposition (VMD) and two deep-learning based methods including Densely Connected Neural Network (DenseNet) model, one-dimensional Vision Transformer (ViT) model, were applied to identify the spinal tissues. The two deep learning methods outperformed the conventional methods with both accuracy over 95%. Especially the signal-based method (ViT) achieved an accuracy of 98.31% and a specificity of 99.2%, and the inference latency was only 0.0025 s. It illustrated the feasibility of applying the forward-oriented ultrasound endoscopic system for real-time intraoperative recognition of critical spinal tissues to enhance the precision and safety of minimally invasive spine surgery.