Search

Abstract Background Sepsis poses a critical threat to hospitalized patients, particularly those in the Intensive Care Unit (ICU). Rapid identification of Sepsis is crucial for improving survival rates. Machine learning techniques offer advantages over traditional methods for predicting outcomes. This study aimed to develop a prognostic model using a Stacking-based Meta-Classifier to predict 30-day mortality risks in Sepsis-3 patients from the MIMIC-III database. Methods A cohort of 4,240 Sepsis-3 patients was analyzed, with 783 experiencing 30-day mortality and 3,457 surviving. Fifteen biomarkers were selected using feature ranking methods, including Extreme Gradient Boosting (XGBoost), Random Forest, and Extra Tree, and the Logistic Regression (LR) model was used to assess their individual predictability with a fivefold cross-validation approach for the validation of the prediction. The dataset was balanced using the SMOTE-TOMEK LINK technique, and a stacking-based meta-classifier was used for 30-day mortality prediction. The SHapley Additive explanations analysis was performed to explain the model’s prediction. Results Using the LR classifier, the model achieved an area under the curve or AUC score of 0.99. A nomogram provided clinical insights into the biomarkers' significance. The stacked meta-learner, LR classifier exhibited the best performance with 95.52% accuracy, 95.79% precision, 95.52% recall, 93.65% specificity, and a 95.60% F1-score. Conclusions In conjunction with the nomogram, the proposed stacking classifier model effectively predicted 30-day mortality in Sepsis patients. This approach holds promise for early intervention and improved outcomes in treating Sepsis cases.

Abstract The growing concern of pediatric mortality demands heightened preparedness in clinical settings, especially within intensive care units (ICUs). As respiratory-related admissions account for a substantial portion of pediatric illnesses, there is a pressing need to predict ICU mortality in these cases. This study based on data from 1188 patients, addresses this imperative using machine learning techniques and investigating different class balancing methods for pediatric ICU mortality prediction. This study employs the publicly accessible “Paediatric Intensive Care database” to train, validate, and test a machine learning model for predicting pediatric patient mortality. Features were ranked using three machine learning feature selection techniques, namely Random Forest, Extra Trees, and XGBoost, resulting in the selection of 16 critical features from a total of 105 features. Ten machine learning models and ensemble techniques are used to make accurate mortality predictions. To tackle the inherent class imbalance in the dataset, we applied a unique data partitioning technique to enhance the model's alignment with the data distribution. The CatBoost machine learning model achieved an area under the curve (AUC) of 72.22%, while the stacking ensemble model yielded an AUC of 60.59% for mortality prediction. The proposed subdivision technique, on the other hand, provides a significant improvement in performance metrics, with an AUC of 85.2% and an accuracy of 89.32%. These findings emphasize the potential of machine learning in enhancing pediatric mortality prediction and inform strategies for improved ICU readiness.

Abstract The early detection of colorectal polyps is crucial for the reduction of mortality rates. However, manually identifying polyps is time-consuming and expensive, increasing the risk of missing them. Our paper aims to address this issue by presenting an automated segmentation approach for colorectal polyps. This paper proposes a method that combines a skip connection with hybrid attention guidance (AG) using attention guidance (AG) and residual path frameworks to identify salient features. Furthermore, we augment test samples using original, horizontal flip, and vertical flip transformations to enhance model robustness through Test Time Augmentation (TTA). The model was trained with Kvasir-seg samples and evaluated on Kvasir-seg and CVC-ClinicDB datasets to gauge generalizability. A significant accuracy (0.9546), a Dice Similarity Coefficient (DSC) of 0.8557, a Cross-section over Union (IoU) of 0.8824, a Recall (0.8221), a Precision (0.8922), an area under Receiver Operating Characteristics (ROC-AUC) of 0.9454, and an area under Precision-Recall (AUC-PR) of 0.8717 were achieved without TTA. Through TTA integration, accuracy (0.9993), DSC (0.8663), IoU (0.8277), Recall (0.8060), Precision (0.9364), and ROC-AUC (0.9587) have been improved. A comparison of our framework with state-of-the-art models demonstrated its effectiveness and segmentation capabilities. Additionally, the proposed model contains only 0.47 million parameters and a weight size of 6.71 MB, illustrating its potential for clinical diagnostics. A computer-aided diagnosis (CAD) system improves patient outcomes by detecting colorectal polyps early and improving segmentation accuracy.

Automatic speech recognition (ASR) plays a pivotal role in our daily lives, offering utility not only for interacting with machines but also for facilitating communication for individuals with partial or profound hearing impairments. The process involves receiving the speech signal in analog form, followed by various signal processing algorithms to make it compatible with devices of limited capacities, such as cochlear implants (CIs). Unfortunately, these implants, equipped with a finite number of electrodes, often result in speech distortion during synthesis. Despite efforts by researchers to enhance received speech quality using various state-of-the-art signal processing techniques, challenges persist, especially in scenarios involving multiple sources of speech, environmental noise, and other adverse conditions. The advent of new artificial intelligence (AI) methods has ushered in cutting-edge strategies to address the limitations and difficulties associated with traditional signal processing techniques dedicated to CIs. This review aims to comprehensively cover advancements in CI-based ASR and speech enhancement, among other related aspects. The primary objective is to provide a thorough overview of metrics and datasets, exploring the capabilities of AI algorithms in this biomedical field, and summarizing and commenting on the best results obtained. Additionally, the review will delve into potential applications and suggest future directions to bridge existing research gaps in this domain.

The increasing prevalence of non-invasive, portable Electroencephalography (EEG) sensors for neuro-physiological measurements has propelled EEG-based assessments of cognitive load (CL) into the spotlight. In this study, we harnessed the capabilities of a four-channel, wearable EEG device that captured brain activity data during two distinct CL states: Baseline (representing a non-CL, resting state) and the Stroop Test (a CL-inducing state). The primary objective of this study is to estimate the CL index through an innovative approach that employs a hybrid, cluster-based, unsupervised learning technique seamlessly integrated with a 1D Convolutional Neural Network (CNN) architecture tailored for automated feature extraction, rather than conventional supervised algorithms, which facilitated in the acquisition of latent complex patterns without the need for manual categorization. The approach was rigorously evaluated using stratified cross-validation, with several assessment criteria assessing both its quality and predictive capability to estimate the CL index. The results obtained (e.g., homogeneity score of 0.7, adjusted rand index of 0.78, silhouette coefficient of 0.5, and an accuracy rate of 93.2%) demonstrate that our module exhibits superiority over supervised approaches. These results are indicative that the adoption of multi-channel wearable EEG devices may facilitate real-time CL estimation, minimizing the need for extensive human intervention, and reducing potential bias, paving the way for more objective and efficient CL assessments.

Brain magnetic resonance imaging (MRI) offers intricate soft tissue contrasts that are essential for diagnosing diseases and conducting neuroscience research. At 7 Tesla (7T) magnetic field intensity, MRI enables increased resolution, enhanced tissue contrast, and improved SNR, compared to MRI collected from the commonly employed 3 Tesla (3T) MRI scanners. However, the exorbitant expenses associated with 7T MRI scanners hinder their broad use in research and clinical facilities. Efforts are underway to develop algorithms that can generate 7T MRI from 3T MRI to achieve better image quality without the need for 7T MRI machines. In this study, we have adopted a cycle consistent generative adversarial network (CycleGAN)-based approach for 3T MRI to 7T MRI translation, and vice versa, using a recently published dataset of paired T1-weighted MR images collected at 3T and 7T from a total of ten subjects. Various CycleGAN architectures were experimented with and compared on this dataset. The best performing CycleGAN architecture successfully produced the reconstructed images with a high level of accuracy based on different quantitative and qualitative evaluation criteria. Utilizing a post-processing technique, the best performing model generated 7T MRI from 3T MRI with a structural similarity index measure (SSIM) of 83.80%, peak SNR (PSNR) of 26.25, normalized mean squared error (NMSE) of 0.0088 and normalized mean absolute error (NMAE) of 0.0630. Utilizing CycleGAN to convert images from 3T to 7T MRI has shown a substantial improvement in MRI resolution, setting the stage for advancements in more informative and precise diagnostic imaging.

Mulberry leaves serve as the primary food source for Bombyx mori silkworms, crucial for silk thread production. However, mulberry trees are highly susceptible to diseases, spreading rapidly and causing significant losses. Manual disease identification across large farms is arduous and time-consuming. Leveraging computer vision for early disease detection and classification can mitigate up to 90% of production losses. This study collected leaves from two regions of Bangladesh, categorized as healthy, leaf rust-affected, and leaf spot-affected. With a total of 1091 images, split into training (764), testing (218), and validation (109) sets for 5-fold cross-validation, preprocessing and augmentation yielded 6,000 images, including synthetics. This study compares ResNet50, VGG19, and MobileNetV3Small on a specific task following architecture modifications. Four convolutional layers with different output channels (512, 128, 64, and 32) were added to baseline models. We assessed how these architectural changes affected model correctness, computing efficiency, and convergence rates. Comparing three pretrained convolutional neural networks (CNNs) - MobileNetV3Small, ResNet50, and VGG19 - augmented with four additional layers, the modified MobileNetV3Small excelled in precision, recall, F1-score, and accuracy, achieving notable results of 97.0%, 96.4%, 96.4%, and 96.4%, respectively, across cross-validation folds. An efficient smartphone application employing the proposed model for mulberry leaf disease recognition was developed. Overall, the model outperformed existing State of the Art (SOTA) approaches, showcasing its effectiveness in disease identification. The interpretative Grad-CAM visualization images match sericulture specialists’ assessments, validating the model’s predictions. These results imply that, this eXplainable AI (XAI) approach with a modified deep learning architecture can appropriately classify mulberry leaves.

Patients with hyperglycemia require routine glucose monitoring to effectively treat their condition. We have developed a lightweight wristband device to capture Photoplethysmography (PPG) signals. We collected PPG signals, demographic information, and blood pressure data from 139 diabetic (49.65%) and non-diabetic (50.35%) subjects. Blood glucose was estimated, and diabetic severity (normal, warning, and dangerous) was stratified using Mel frequency cepstral coefficients, time, frequency, and statistical features from PPG and their derivative signals along with physiological parameters. Bagged Ensemble Trees outperform other algorithms in estimating blood glucose level with a correlation coefficient of 0.90. The proposed model’s prediction was all in Zone A and B in the Clarke Error Grid analysis. The predictions are thus clinically acceptable. Furthermore, K-nearest neighbor model classified the severity levels with an accuracy of 98.12%. Furthermore, the proposed models were deployed in Amazon Web Server. The wristband is connected to an Android mobile application to collect real-time data and update the estimated glucose and diabetic severity every 10-seconds, which will allow the users to gain better control of their diabetic health.

The emergence of COVID-19 resulted in significant shortages of mechanical ventilators globally. This prompted investigations into developing new, cost-effective methods for producing ventilators. Different types of ventilators, such as positive pressure ventilators (PPVs), conventional negative pressure ventilators (NPVs), and biphasic cuirass ventilators (BCVs), were considered. However, PPVs were found to pose health risks and were expensive to manufacture. Thus, this study introduces ExoventQ, an innovative respiratory support device inspired by traditional NPV designs. ExoventQ was meticulously designed, simulated, implemented, and tested in two modes: continuous negative extrathoracic pressure (CNEP) and cyclic negative pressure ventilation (CNPV). It consists of three main components: a pressure vessel, a pumping system, and a control panel. Each component was designed with attention to pressure distribution, material, safety, cost, and portability. Through ANSYS stress analysis, ExoventQ was developed with a squircle-shaped polycarbonate vessel capable of withstanding up to 50 millibar (mbar) of vacuum pressure. This design also prevents airway tilting when placed on its side, providing more comfort for the patient. Pressure regulation inside the vessel is achieved through a bypass butterfly valve controlled by a servo motor. The user interface is implemented on a Raspberry Pi touchscreen, enabling input through rotating knobs and displaying output for monitoring. Safety measures include audio and visual alarms, along with a power switch that halts ventilation if the vacuum in the vessel drops below 40 mbar. The successful design and implementation of ExoventQ have the potential to enable mass production of safe and affordable NPVs to address pulmonary complications.

Virtual reality (VR) is the employment of computer devices to simulate real or imaginary environments. Conventional user interfaces stress the usage of screen displays to interact with the developed environment. The prospect of VR enables the user to be virtually inside the environment. Cave automatic virtual reality environment (CAVE) is one kind of room-shaped VR technology that displays the environment on its walls. We observe some common limitations in the existing CAVE technology, such as fixed space requirements, and the difficulty in moving it. In this paper, we present a novel mobile-CAVE system that uses light-weighted materials and portable powered devices. It solves the limitation of re-using the allocated space by packing it and the ability to move it easily. We have assessed our technology by performing usability analysis, power consumption, and mobility experimental study. The profound experiments demonstrated the efficiency of the proposed technology in comparison with the former CAVE system.

Chest surface vibrations induced by cardiac activities can provide valuable insights into various heart conditions. Seismocardiogram (SCG) and Gyrocardiogram (GCG) signals, collectively referred to as Mechanocardiograms (MCG) and collected using a chest-mounted accelerometer and gyroscope, respectively, have the potential to serve as an effective alternative to Electrocardiograms (ECG) for continuous cardiac monitoring. In many cases, both modalities (MCG and ECG) can be used in tandem to monitor cardiac functions in both healthy subjects and Intensive Care Unit (ICU) patients. Direct acquisition of ECGs can be challenging in certain scenarios, such as with wearable devices, or due to issues with disconnections arising from loose contact surfaces or gel corrosion during long-term usage. ECG considered the gold standard for heart monitoring, is essential for a comprehensive assessment of cardiac parameters and patient health. MCGs have the potential to reliably estimate ECGs and can replace direct ECG acquisition procedures in such cases. In this study, we introduce M2ECG, a 1D-segmentation-based approach for translating ECG signals from the corresponding MCG signals acquired by an Inertial Measurement Unit (IMU) attached to the chest wall. Using the proposed SA-UNet, we achieved an average Pearson Correlation Coefficient (PCC) of 81.76% on a subject-independent test set. We also compared the estimated heart rates (HR) from the reconstructed ECGs to the ground truth ECGs to validate our model’s performance. The overall HR correlation achieved on the subject-independent test set was around 94.167%. The highest correlation of the HR and HRV calculated from the translated and the ground truth ECGs were around 99.073% and 96.289%, respectively for the best test case. The strong correlation observed in cardiac parameters (HR, HRV) underscores the effectiveness of MCG, suggesting its potential use for continuous monitoring of cardiac patients.

In response to the growing waste problem caused by industrialization and modernization, the need for an automated waste sorting and recycling system for sustainable waste management has become ever more pressing. Deep learning has made significant advancements in image classification, making it ideally suited for waste sorting applications. This application depends on the development of a suitable deep learning model capable of accurately categorizing various categories of waste. In this study, we present RWC-Net (recyclable waste classification network), a novel deep learning model designed for the classification of six distinct waste categories using the TrashNet dataset of 2,527 images of waste. The performance of our model is subjected to intensive quantitative and qualitative evaluations and is compared to various state-of-art waste classification techniques. The proposed model outperformed several state-of-the-art models by obtaining a remarkable overall accuracy rate of 95.01 percent. In addition, it receives high F1-scores for each of the six waste categories: 97.24% for cardboard, 96.18% for glass, 94% for metal, 95.73% for paper, 93.67% for plastic, and 88.55% for litter. The reliability of the model is demonstrated qualitatively through the saliency maps generated by Score-CAM (class activation mapping) model, which provide visual insights into its performance across various waste categories. These results highlight the model’s accuracy and demonstrate its potential as an effective automated waste classification and management solution.

Rotating machines require bearings to operate smoothly. However, wear, misalignment, and poor lubrication can degrade bearings over time. Fault diagnosis models identify and classify bearing faults. A fault diagnosis model trained in a specific working condition may not perform well in different working conditions. Real-world datasets are mixed with various work environment conditions; therefore, validating a model using different working conditions datasets is necessary. In this study, raw vibrational accelerometer data of variable working conditions is preprocessed using the window length and stride method to generate a data format suitable for evaluating the proposed model. This model employs the Transfer learning-based VGG16 model as the feature extractor and random forest as the classifier, and it has proven to be highly effective. This proposed fault diagnosis model adapts to different work environments and enhances fault classification at variable working conditions. The performance of the proposed model is evaluated using various metrics such as confusion matrix heatmap, t-SNE plot, precision-recall curve and learning curve. Results obtained from these metrics indicate that this model performs well compared to others. The overall accuracy of the model is 99.90%, and both the training and testing of this model are fast. It is evident from the learning curve evaluation that this model is free from over- or under-fitting issues. Overall, this model is reliable and suitable for classifying bearing faults at different working conditions and can be useable for real world purposes.

Tomatoes are the most widely grown crop in the world, and they may be found in a variety of forms in every kitchen, regardless of cuisine. It is, after potato and sweet potato, the most widely farmed crop on the planet. Cotton is another essential cash crop because most farmers grow it in huge quantities. However, many diseases reduce the quality and quantity of tomato and cotton crops, resulting in a significant loss in production and productivity. It is critical to detect these disorders at an early stage of diagnosis. The purpose of this work is to categorize 14 classes for both cotton and tomato crops, with 12 diseased classes and two healthy classes using a deep learning-based lightweight 2D CNN architecture and to implement the model in an android application named “Plant Disease Classifier” for smartphone-assisted plant disease diagnosis system, the results of the experiments reveal that the proposed model outperforms the pre-trained models VGG16, VGG19 and InceptionV3 despite having fewer parameters. With slightly larger parameters than MobileNet and MobileNetV2, proposed model also attains considerably larger accuracy than these models. The classification accuracy varies between 57% and 92% for these models, and the proposed model’s average accuracy is 97.36%. Also, the precision, recall, F1-score of the proposed model is 97 % and Area Under Curve (AUC) score of the model is 99.9% which is an indicator of the very good performance of the model. Class activation maps were shown using the Gradient Weighted Class Activation Mapping (Grad-CAM) technique to visually explain the disease detected by the proposed model, and a heatmap was produced to indicate the responsible region for classification. The app works very impressively and classified the correct disease in a shorter period of time of about 4.84 ms due to the lightweight nature of the model.

Congenital heart defects (CHDs) are a leading cause of death in infants under 1 year of age. Prenatal intervention can reduce the risk of postnatal serious CHD patients, but current diagnosis is based on qualitative criteria, which can lead to variability in diagnosis between clinicians. Objectives: To detect morphological and temporal changes in cardiac ultrasound (US) videos of fetuses with hypoplastic left heart syndrome (HLHS) using deep learning models. A small cohort of 9 healthy and 13 HLHS patients were enrolled, and ultrasound videos at three gestational time points were collected. The videos were preprocessed and segmented to cardiac cycle videos, and five different deep learning CNN-LSTM models were trained (MobileNetv2, ResNet18, ResNet50, DenseNet121, and GoogleNet). The top-performing three models were used to develop a novel stacking CNN-LSTM model, which was trained using five-fold cross-validation to classify HLHS and healthy patients. The stacking CNN-LSTM model outperformed other pre-trained CNN-LSTM models with the accuracy, precision, sensitivity, F1 score, and specificity of 90.5%, 92.5%, 92.5%, 92.5%, and 85%, respectively for video-wise classification, and with the accuracy, precision, sensitivity, F1 score, and specificity of 90.5%, 92.5%, 92.5%, 92.5%, and 85%, respectively for subject-wise classification using ultrasound videos. This study demonstrates the potential of using deep learning models to classify CHD prenatal patients using ultrasound videos, which can aid in the objective assessment of the disease in a clinical setting.

To determine head pose within an MR scanner using measurements of gradient-induced voltage from a multiple coil. A practical implementation of this approach would involve measuring the position-sensitive voltages induced by the imaging gradients rather than additional gradient pulses. This would speed up the model formation phase and increase the temporal resolution of position monitoring. We propose a novel method to measure the gradient-induced voltages in a set of five coils to estimate the position and orientations (POS) into MR scanner. A training set of measurements was first made and then Principal Component Analysis (PCA) was applied to the POS data estimated by using Statistical Parametric Mapping (SPM8), and the principal components were collected into a design matrix. Experimental data were collected and then the coefficients derived from the training set were used to estimate the POS changes and the results compared to movement parameters found using image co-registration. The changes in POS estimated from SPM8 co-registration and from the measured voltages for the phantom and the subject. The differences in the positions were estimated by using SPM8 and the model relating the change in induced voltages to position. The range and root-mean-square (RMS) amplitude of these differences for the phantom/subject data. The results suggest that it is possible to estimate the position and orientation with 0.22mm and 0.24° root-mean-square error using this set-up. The new approach could be used for prospective or retrospective motion correction.

Electrooculography, also known as EOG, is a technique that is used to calculate the corneo-retinal standing potential, which is located between the cornea and the retina of the human eye. Applications of EOG include eye disease diagnosis and eye movement tracking. There has been various research on reading activity detection from EOG signals in controlled laboratory settings. However, determining reading behaviours from data collected from real-world environments remains a challenging problem. Detecting reading in practical scenarios can lead us to track our daily reading activity, thereby improving our learning experience and even workplace productivity. Tracking regular reading behaviour can also lead to further research in cognitive psychology, literacy development, reading motivation, and reading comprehension. In this study, we investigated an electrooculogram dataset that was collected on the field from 10 users who were engaged in their daily activities on two separate days. We propose a pipeline combining the statistical features with deep learning features from pre-trained ImageNet models. To detect the fine-grained reading activities, we adopted a nested classification approach. Initially, we differentiate between reading and not reading and then we employ an additional classification step to discriminate among three distinct types of reading activities. With our pipeline, we could achieve 66.56% accuracy in detecting the reading activities whereas the original dataset publication showed a baseline performance of only 32%.

This proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a Field-Programmable Gate Array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existing neural network models in terms of energy and resource efficiency, by exploring the potential of FPGA-based hardware acceleration in conjunction with advanced neural network architectures like CVNNs. The methodological innovation of this research lies in the Cartesian to polar transformation of 2D images, effectively reducing the input data volume required for neural network processing. Subsequent efforts focused on constructing a CVNN model optimized for FPGA implementation, emphasizing the enhancement of computational efficiency and overall performance. The experimental findings provide empirical evidence supporting the efficacy of the image classification system developed in this study. One of the developed models, CVNN_128, achieves an accuracy of 88.3% with an inference time of just 1.6 ms and a power consumption of 4.66 mW for the classification of the MNIST test dataset, which consists of 10,000 frames. While there is a slight concession in accuracy compared to recent FPGA implementations that achieve 94.43%, our model significantly excels in classification speed and power efficiency—surpassing existing models by more than a factor of 100. In conclusion, this paper demonstrates the substantial advantages of the FPGA implementation of CVNNs for image classification tasks, particularly in scenarios where speed, resource, and power consumption are critical.

Mulberry leaves feed Bombyx mori silkworms to generate silk thread. Diseases that affect mulberry leaves have reduced crop and silk yields in sericulture, which produces 90% of the world’s raw silk. Manual leaf disease identification is tedious and error-prone. Computer vision can categorize leaf diseases early and overcome the challenges of manual identification. No mulberry leaf deep learning (DL) models have been reported. Therefore, in this study, two types of leaf diseases: leaf rust and leaf spot, with disease-free leaves, were collected from two regions of Bangladesh. Sericulture experts annotated the leaf images. The images were pre-processed, and 6,000 synthetic images were generated using typical image augmentation methods from the original 764 training images. Additional 218 and 109 images were employed for testing and validation respectively. In addition, a unique lightweight parallel depth-wise separable CNN model, PDS-CNN was developed by applying depth-wise separable convolutional layers to reduce parameters, layers, and size while boosting classification performance. Finally, the explainable capability of PDS-CNN is obtained through the use of SHapley Additive exPlanations (SHAP) evaluated by a sericulture specialist. The proposed PDS-CNN outperforms well-known deep transfer learning models, achieving an optimistic accuracy of 95.05 ± 2.86% for three-class classifications and 96.06 ± 3.01% for binary classifications with only 0.53 million parameters, 8 layers, and a size of 6.3 megabytes. Furthermore, when compared with other well-known transfer models, the proposed model identified mulberry leaf diseases with higher accuracy, fewer factors, fewer layers, and lower overall size. The visually expressive SHAP explanation images validate the models’ findings aligning with the predictions made the sericulture specialist. Based on these findings, it is possible to conclude that the explainable AI (XAI)-based PDS-CNN can provide sericulture specialists with an effective tool for accurately categorizing mulberry leaves.

Abstract Background Acinetobacter calcoaceticus-A. baumannii (ACB) complex pathogens are known for their prevalence in nosocomial infections and extensive antimicrobial resistance (AMR) capabilities. While genomic studies worldwide have elucidated the genetic context of antibiotic resistance in major international clones (ICs) of clinical Acinetobacter spp., not much information is available from Bangladesh. In this study, we analysed the AMR profiles of 63 ACB complex strains collected from Dhaka, Bangladesh. Following this, we generated draft genomes of 15 of these strains to understand the prevalence and genomic environments of AMR, virulence and mobilization associated genes in different Acinetobacter clones. Results Around 84% (n = 53) of the strains were extensively drug resistant (XDR) with two showing pan-drug resistance. Draft genomes generated for 15 strains confirmed 14 to be A. baumannii while one was A. nosocomialis. Most A. baumannii genomes fell under three clonal complexes (CCs): the globally dominant CC1 and CC2, and CC10; one strain had a novel sequence type (ST). AMR phenotype-genotype agreement was observed and the genomes contained various beta-lactamase genes including bla OXA-23 (n = 12), bla OXA-66 (n = 6), and bla NDM-1 (n = 3). All genomes displayed roughly similar virulomes, however some virulence genes such as the Acinetobactin bauA and the type IV pilus gene pilA displayed high genetic variability. CC2 strains carried highest levels of plasmidic gene content and possessed conjugative elements carrying AMR genes, virulence factors and insertion sequences. Conclusion This study presents the first comparative genomic analysis of XDR clinical Acinetobacter spp. from Bangladesh. It highlights the prevalence of different classes of beta-lactamases, mobilome-derived heterogeneity in genetic architecture and virulence gene variability in prominent Acinetobacter clonal complexes in the country. The findings of this study would be valuable in understanding the genomic epidemiology of A. baumannii clones and their association with closely related pathogenic species like A. nosocomialis in Bangladesh.

Abstract In this paper, proposes a microwave brain imaging system to detect brain tumors using a metamaterial (MTM) loaded three-dimensional (3D) stacked wideband antenna array. The antenna is comprised of metamaterial-loaded with three substrate layers, including two air gaps. One 1 × 4 MTM array element is used in the top layer and middle layer, and one 3 × 2 MTM array element is used in the bottom layer. The MTM array elements in layers are utilized to enhance the performance concerning antenna’s efficiency, bandwidth, realized gain, radiation directionality in free space and near the head model. The antenna is fabricated on cost-effective Rogers RT5880 and RO4350B substrate, and the optimized dimension of the antenna is 50 × 40 × 8.66 mm3. The measured results show that the antenna has a fractional bandwidth of 79.20% (1.37–3.16 GHz), 93% radiation efficiency, 98% high fidelity factor, 6.67 dBi gain, and adequate field penetration in the head tissue with a maximum of 0.0018 W/kg specific absorption rate. In addition, a 3D realistic tissue-mimicking head phantom is fabricated and measured to verify the performance of the antenna. Later, a nine-antenna array-based microwave brain imaging (MBI) system is implemented and investigated by using phantom model. After that, the scattering parameters are collected, analyzed, and then processed by the Iteratively Corrected delay-multiply-and-sum algorithm to detect and reconstruct the brain tumor images. The imaging results demonstrated that the implemented MBI system can successfully detect the target benign and malignant tumors with their locations inside the brain.

ObjectiveDevelop a reliable, automated deep learning-based method for accurate measurement of penile curvature (PC) using 2-dimensional images.Materials and methodsA set of nine 3D-printed models was used to generate a batch of 913 images of penile curvature (PC) with varying configurations (curvature range 18° to 86°). The penile region was initially localized and cropped using a YOLOv5 model, after which the shaft area was extracted using a UNet-based segmentation model. The penile shaft was then divided into three distinct predefined regions: the distal zone, curvature zone, and proximal zone. To measure PC, we identified four distinct locations on the shaft that reflected the mid-axes of proximal and distal segments, then trained an HRNet model to predict these landmarks and calculate curvature angle in both the 3D-printed models and masked segmented images derived from these. Finally, the optimized HRNet model was applied to quantify PC in medical images of real human patients and the accuracy of this novel method was determined.ResultsWe obtained a mean absolute error (MAE) of angle measurement

This research investigates the implementation of complex-exponential-based neurons in FPGA, which can pave the way for implementing bio-inspired spiking neural networks to compensate for the existing computational constraints in conventional artificial neural networks. The increasing use of extensive neural networks and the complexity of models in handling big data lead to higher power consumption and delays. Hence, finding solutions to reduce computational complexity is crucial for addressing power consumption challenges. The complex exponential form effectively encodes oscillating features like frequency, amplitude, and phase shift, streamlining the demanding calculations typical of conventional artificial neurons through levering the simple phase addition of complex exponential functions. The article implements such a two-neuron and a multi-neuron neural model using the Xilinx System Generator and Vivado Design Suite, employing 8-bit, 16-bit, and 32-bit fixed-point data format representations. The study evaluates the accuracy of the proposed neuron model across different FPGA implementations while also providing a detailed analysis of operating frequency, power consumption, and resource usage for the hardware implementations. BRAM-based Vivado designs outperformed Simulink regarding speed, power, and resource efficiency. Specifically, the Vivado BRAM-based approach supported up to 128 neurons, showcasing optimal LUT and FF resource utilization. Such outcomes accommodate choosing the optimal design procedure for implementing spiking neural networks on FPGAs.

The human liver exhibits variable characteristics and anatomical information, which is often ambiguous in radiological images. Machine learning can be of great assistance in automatically segmenting the liver in radiological images, which can be further processed for computer-aided diagnosis. Magnetic resonance imaging (MRI) is preferred by clinicians for liver pathology diagnosis over volumetric abdominal computerized tomography (CT) scans, due to their superior representation of soft tissues. The convenience of Hounsfield unit (HoU) based preprocessing in CT scans is not available in MRI, making automatic segmentation challenging for MR images. This study investigates multiple state-of-the-art segmentation networks for liver segmentation from volumetric MRI images. Here, T1-weighted (in-phase) scans are investigated using expert-labeled liver masks from a public dataset of 20 patients (647 MR slices) from the Combined Healthy Abdominal Organ Segmentation grant challenge (CHAOS). The reason for using T1-weighted images is that it demonstrates brighter fat content, thus providing enhanced images for the segmentation task. Twenty-four different state-of-the-art segmentation networks with varying depths of dense, residual, and inception encoder and decoder backbones were investigated for the task. A novel cascaded network is proposed to segment axial liver slices. The proposed framework outperforms existing approaches reported in the literature for the liver segmentation task (on the same test set) with a dice similarity coefficient (DSC) score and intersect over union (IoU) of 95.15% and 92.10%, respectively.

The exploration of nanocellulose has been aided by rapid nanotechnology and material science breakthroughs, resulting in their emergence as desired biomaterials. Nanocellulose has been thoroughly studied in various disciplines, including renewable energy, electronics, environment, food production, biomedicine, healthcare, and so on. Cellulose nanocrystal (CNC) is a part of the organic crystallization of macromolecular compounds found in bacteria’s capsular polysaccharides and plant fibers. Owing to numerous reactive chemical groups on its surface, physical adsorption, surface grating, and chemical vapor deposition can all be used to increase its performance, which is the key reason for its wide range of applications. Cellulose nanocrystals (CNCs) have much potential as suitable matrices and advanced materials, and they have been utilized so far, both in terms of modifying and inventing uses for them. This work reviews CNC’s synthesis, properties and various industrial applications. This review has also discussed the widespread applications of CNC as sensor, acoustic insulator, and fire retardant material.

Physiological signal measurement and processing are increasingly becoming popular in the ambulatory setting as the hospital-centric treatment is moving towards wearable and ubiquitous monitoring. Most of the physiological signals are highly susceptible to various types of noises, especially movement artifacts. The electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals are no exception to motion artifacts, which become prominent in the ambulatory setting. Since successful detection of various neurological disorders is greatly dependent upon clean EEG and fNIRS signals, it is a matter of utmost importance to remove motion artifacts from these two signal modalities using reliable and robust methods. This paper proposes three novel multiresolution analysis techniques: i) Variational mode decomposition (VMD), ii) VMD in combination with principal component analysis (VMD-PCA), and iii) VMD in combination with canonical correlation analysis (VMD-CCA), for motion artifact correction from single-channel EEG and fNIRS signals. The efficacy of these novel techniques is validated by computing the difference in the signal to noise ratio ( $\Delta SNR$ ) and percentage reduction in motion artifacts ( $\eta$ ). Among the three proposed novel methods, VMD-CCA decomposed with 15 intrinsic mode functions (IMFs) has shown the best denoising performance for EEG signals producing an average $\Delta SNR$ and $\eta $ values of 23.81 dB and 57.01%, respectively for all 23 EEG recordings. On the other hand, for the available 16 fNIRS recordings, VMD-CCA decomposed with 10 IMFs produced an average $\Delta SNR$ and $\eta $ values of 15.97 dB and 39.01%, respectively. The results reported using the proposed methods outperform most of the existing state-of-the-art techniques.

Radiographic images are commonly used to detect aseptic loosening of the hip implant in patients with total hip replacement (THR) surgeries. These techniques of manual assessment by medical professionals can suffer from the drawback of low accuracy, poor inter-observer reliability, and delays due to the unavailability of experienced clinicians. Thus, the paper provides a reliable Deep Convolutional Neural Networks (DCNNs) based novel stacking approach (HipXNet) for detecting loosening of the hip implant using X-ray images. Two major investigations were done in this study. Firstly, the performance of four different state-of-the-art object detection YOLOv5 models was evaluated to detect the implant region from the hip X-ray images. Secondly, the study developed a stacking classifier using three different Convolutional neural networks (CNN) models to classify aseptic hip loosening and compared the performance with eight different state-of-the-art CNN networks. Moreover, one publicly accessible dataset with two sub-sets was created for these two experiments, where 200 hip implant X-ray images were collected and annotated by two expert radiologists for implant detection and 206 hip implant X-ray images were collected for loosening detection. YOLOv5m model outperformed the other variants of YOLOv5 to detect the implant region with the precision, recall, mean average precision (mAP)0.5, mAP0.5–0.95 of 100%, 100%, 100%, and 87.8%, respectively. Densenet201 CNN model outperformed other CNN models with the accuracy, precision, sensitivity, F1 score, and specificity of 94.66%, 94.66%, 94.66%, 94.66%, and 94.5%, respectively while the stacking technique with Random Forest meta learner classifier produced the best performance with the accuracy, precision, sensitivity, F1 score and specificity of 96.11%, 96.42%, 96.42%, 96.42%, and 96.74% respectively for loosening detection. The reliability of the performance was confirmed by the popular Score-CAM visualization. This study can help in the early and fast identification of hip implant loosening with the help of simple X-ray images and computed aided diagnosis.

Colorectal polyps in the colon or rectum are precancerous growths that can lead to a more severe disease called colorectal cancer. Accurate segmentation of polyps using medical imaging data is essential for effective diagnosis. However, manual segmentation by endoscopists can be time-consuming, error-prone, and expensive, leading to a high rate of missed anomalies. To solve this problem, an automated diagnostic system based on deep learning algorithms is proposed to find polyps. The proposed IRv2-Net model is developed using the UNet architecture with a pre-trained InceptionResNetV2 encoder to extract most features from the input samples. The Test Time Augmentation (TTA) technique, which utilizes the characteristics of the original, horizontal, and vertical flips, is used to gain precise boundary information and multi-scale image features. The performance of numerous state-of-the-art (SOTA) models is compared using several metrics such as accuracy, Dice Similarity Coefficients (DSC), Intersection Over Union (IoU), precision, and recall. The proposed model is tested on the Kvasir-SEG and CVC-ClinicDB datasets, demonstrating superior performance in handling unseen real-time data. It achieves the highest area coverage in the area under the Receiver Operating Characteristic (ROC-AUC) and area under Precision-Recall (AUC-PR) curves. The model exhibits excellent qualitative testing outcomes across different types of polyps, including more oversized, smaller, over-saturated, sessile, or flat polyps, within the same dataset and across different datasets. Our approach can significantly minimize the number of missed rating difficulties. Lastly, a graphical interface is developed for producing the mask in real-time. The findings of this study have potential applications in clinical colonoscopy procedures and can serve based on further research and development.

Background: Sepsis, a life-threatening infection-induced inflammatory condition, has significant global health impacts. Timely detection is crucial for improving patient outcomes as sepsis can rapidly progress to severe forms. The application of machine learning (ML) and deep learning (DL) to predict sepsis using electronic health records (EHRs) has gained considerable attention for timely intervention. Methods: PubMed, IEEE Xplore, Google Scholar, and Scopus were searched for relevant studies. All studies that used ML/DL to detect or early-predict the onset of sepsis in the adult population using EHRs were considered. Data were extracted and analyzed from all studies that met the criteria and were also evaluated for their quality. Results: This systematic review examined 1942 articles, selecting 42 studies while adhering to strict criteria. The chosen studies were predominantly retrospective (n = 38) and spanned diverse geographic settings, with a focus on the United States. Different datasets, sepsis definitions, and prevalence rates were employed, necessitating data augmentation. Heterogeneous parameter utilization, diverse model distribution, and varying quality assessments were observed. Longitudinal data enabled early sepsis prediction, and quality criteria fulfillment varied, with inconsistent funding–article quality correlation. Conclusions: This systematic review underscores the significance of ML/DL methods for sepsis detection and early prediction through EHR data.

Every one of us has a unique manner of communicating to explore the world, and such communication helps to interpret life. Sign language is the popular language of communication for hearing and speech-disabled people. When a sign language user interacts with a non-sign language user, it becomes difficult for a signer to express themselves to another person. A sign language recognition system can help a signer to interpret the sign of a non-sign language user. This study presents a sign language recognition system that is capable of recognizing Arabic Sign Language from recorded RGB videos. To achieve this, two datasets were considered, such as (1) the raw dataset and (2) the face–hand region-based segmented dataset produced from the raw dataset. Moreover, operational layer-based multi-layer perceptron “SelfMLP” is proposed in this study to build CNN-LSTM-SelfMLP models for Arabic Sign Language recognition. MobileNetV2 and ResNet18-based CNN backbones and three SelfMLPs were used to construct six different models of CNN-LSTM-SelfMLP architecture for performance comparison of Arabic Sign Language recognition. This study examined the signer-independent mode to deal with real-time application circumstances. As a result, MobileNetV2-LSTM-SelfMLP on the segmented dataset achieved the best accuracy of 87.69% with 88.57% precision, 87.69% recall, 87.72% F1 score, and 99.75% specificity. Overall, face–hand region-based segmentation and SelfMLP-infused MobileNetV2-LSTM-SelfMLP surpassed the previous findings on Arabic Sign Language recognition by 10.970% accuracy.

The carotid artery is a major blood vessel that supplies blood to the brain. Plaque buildup in the arteries can lead to cardiovascular diseases such as atherosclerosis, stroke, ruptured arteries, and even death. Both invasive and non-invasive methods are used to detect plaque buildup in the arteries, with ultrasound imaging being the first line of diagnosis. This paper presents a comprehensive review of the existing literature on ultrasound image analysis methods for detecting and characterizing plaque buildup in the carotid artery. The review includes an in-depth analysis of datasets; image segmentation techniques for the carotid artery plaque area, lumen area, and intima–media thickness (IMT); and plaque measurement, characterization, classification, and stenosis grading using deep learning and machine learning. Additionally, the paper provides an overview of the performance of these methods, including challenges in analysis, and future directions for research.

Intracranial hemorrhage (ICH) occurs when blood leaks inside the skull as a result of trauma to the skull or due to medical conditions. ICH usually requires immediate medical and surgical attention because the disease has a high mortality rate, long-term disability potential, and other potentially life-threatening complications. There are a wide range of severity levels, sizes, and morphologies of ICHs, making accurate identification challenging. Hemorrhages that are small are more likely to be missed, particularly in healthcare systems that experience high turnover when it comes to computed tomography (CT) investigations. Although many neuroimaging modalities have been developed, CT remains the standard for diagnosing trauma and hemorrhage (including non-traumatic ones). A CT scan-based diagnosis can provide time-critical, urgent ICH surgery that could save lives because CT scan-based diagnoses can be obtained rapidly. The purpose of this study is to develop a machine-learning algorithm that can detect intracranial hemorrhage based on plain CT images taken from 75 patients. CT images were preprocessed using brain windowing, skull-stripping, and image inversion techniques. Hemorrhage segmentation was performed using multiple pre-trained models on preprocessed CT images. A U-Net model with DenseNet201 pre-trained encoder outperformed other U-Net, U-Net++, and FPN (Feature Pyramid Network) models with the highest Dice similarity coefficient (DSC) and intersection over union (IoU) scores, which were previously used in many other medical applications. We presented a three-dimensional brain model highlighting hemorrhages from ground truth and predicted masks. The volume of hemorrhage was measured volumetrically to determine the size of the hematoma. This study is essential in examining ICH for diagnostic purposes in clinical practice by comparing the predicted 3D model with the ground truth.

Aortic valve defects are among the most prevalent clinical conditions. A severely damaged or non-functioning aortic valve is commonly replaced with a bioprosthetic heart valve (BHV) via the transcatheter aortic valve replacement (TAVR) procedure. Accurate pre-operative planning is crucial for a successful TAVR outcome. Assessment of computational fluid dynamics (CFD), finite element analysis (FEA), and fluid–solid interaction (FSI) analysis offer a solution that has been increasingly utilized to evaluate BHV mechanics and dynamics. However, the high computational costs and the complex operation of computational modeling hinder its application. Recent advancements in the deep learning (DL) domain can offer a real-time surrogate that can render hemodynamic parameters in a few seconds, thus guiding clinicians to select the optimal treatment option. Herein, we provide a comprehensive review of classical computational modeling approaches, medical imaging, and DL approaches for planning and outcome assessment of TAVR. Particularly, we focus on DL approaches in previous studies, highlighting the utilized datasets, deployed DL models, and achieved results. We emphasize the critical challenges and recommend several future directions for innovative researchers to tackle. Finally, an end-to-end smart DL framework is outlined for real-time assessment and recommendation of the best BHV design for TAVR. Ultimately, deploying such a framework in future studies will support clinicians in minimizing risks during TAVR therapy planning and will help in improving patient care.

Abstract A novel and systematic procedure to design a co-polarized electromagnetic metamaterial (MM) absorber with desired outputs and resonance frequencies for dual-band WiFi signal absorption is presented. The desired resonance frequencies with expected S parameters' values were first designed as an equivalent circuit with extensive analysis and then implemented into frequency-selective MM absorber by numerical simulation with precise LRC elements, satisfying least unit cell area (0.08λ), substrate thickness (0.01λ) and maximum effective medium ratio (12.49). The absorber was simulated for the maximum angle of incidence for both the normal and oblique incidences at co-polarization. The absorptions at the desired resonance frequencies were found at a satisfactory level by both simulation and practical measurement along with a single negative value to ensure metamaterial characteristics. The proposed equivalent circuit analysis approach can help researchers design and engineering co-polarization insensitive MM absorbers using conventional split-ring resonators, with perfection in output and desired resonance frequencies without the necessity of lumped elements or multilayer substrates. The proposed metamaterial can be utilized for SAR reduction, crowdsensing, and other WiFi-related practical applications.

ObjectiveTo develop and validate an artificial intelligence (AI)-based algorithm for capturing automated measurements of Penile curvature (PC) based on 2-dimensional images.Materials and methodsNine 3D-printed penile models with differing curvature angles (ranging from 18 to 88°) were used to compile a 900-image dataset featuring multiple camera positions, inclination angles, and background/lighting conditions. The proposed framework of PC angle estimation consisted of three stages: automatic penile area localization, shaft segmentation, and curvature angle estimation. The penile model images were captured using a smartphone camera and used to train and test a Yolov5 model that automatically cropped the penile area from each image. Next, an Unet-based segmentation model was trained, validated, and tested to segment the penile shaft, before a custom Hough-Transform-based angle estimation technique was used to evaluate degree of PC.ResultsThe proposed framework displayed robust performance in cropping the penile area [mean average precision (mAP) 99.4%] and segmenting the shaft [Dice Similarity Coefficient (DSC) 98.4%]. Curvature angle estimation technique generally demonstrated excellent performance, with a mean absolute error (MAE) of just 8.5 when compared with ground truth curvature angles.ConclusionsConsidering current intra- and inter-surgeon variability of PC assessments, the framework reported here could significantly improve precision of PC measurements by surgeons and hypospadiology researchers.

Kidney cancers are one of the most common malignancies worldwide. Accurate diagnosis is a critical step in the management of kidney cancer patients and is influenced by multiple factors including tumor size or volume, cancer types and stages, etc. For malignant tumors, partial or radical surgery of the kidney might be required, but for clinicians, the basis for making this decision is often unclear. Partial nephrectomy could result in patient death due to cancer if kidney removal was necessary, whereas radical nephrectomy in less severe cases could resign patients to lifelong dialysis or need for future transplantation without sufficient cause. Using machine learning to consider clinical data alongside computed tomography images could potentially help resolve some of these surgical ambiguities, by enabling a more robust classification of kidney cancers and selection of optimal surgical approaches. In this study, we used the publicly available KiTS dataset of contrast-enhanced CT images and corresponding patient metadata to differentiate four major classes of kidney cancer: clear cell (ccRCC), chromophobe (chRCC), papillary (pRCC) renal cell carcinoma, and oncocytoma (ONC). We rationalized these data to overcome the high field of view (FoV), extract tumor regions of interest (ROIs), classify patients using deep machine-learning models, and extract/post-process CT image features for combination with clinical data. Regardless of marked data imbalance, our combined approach achieved a high level of performance (85.66% accuracy, 84.18% precision, 85.66% recall, and 84.92% F1-score). When selecting surgical procedures for malignant tumors (RCC), our method proved even more reliable (90.63% accuracy, 90.83% precision, 90.61% recall, and 90.50% F1-score). Using feature ranking, we confirmed that tumor volume and cancer stage are the most relevant clinical features for predicting surgical procedures. Once fully mature, the approach we propose could be used to assist surgeons in performing nephrectomies by guiding the choices of optimal procedures in individual patients with kidney cancer.

Transcranial doppler (TCD) ultrasound is a non-invasive imaging technique that can be used for continuous monitoring of blood flow in the brain through the major cerebral arteries by calculating the cerebral blood flow velocity (CBFV). Since the brain requires a consistent supply of blood to function properly and meet its metabolic demand, a change in CBVF can be an indication of neurological diseases. Depending on the severity of the disease, the symptoms may appear immediately or may appear weeks later. For the early detection of neurological diseases, a classification model is proposed in this study, with the ability to distinguish healthy subjects from critically ill subjects. The TCD ultrasound database used in this study contains signals from the middle cerebral artery (MCA) of 6 healthy subjects and 12 subjects with known neurocritical diseases. The classification model works based on the maximal blood flow velocity waveforms extracted from the TCD ultrasound. Since the signal quality of the recorded TCD ultrasound is highly dependent on the operator’s skillset, a noisy and corrupted signal can exist and can add biases to the classifier. Therefore, a deep learning classifier, trained on a curated and clean biomedical signal can reliably detect neurological diseases. For signal classification, this study proposes a Self-organized Operational Neural Network (Self-ONN)-based deep learning model Self-ResAttentioNet18, which achieves classification accuracy of 96.05% with precision, recall, f1 score, and specificity of 96.06%, 96.05%, 96.06%, and 96.09%, respectively. With an area under the ROC curve of 0.99, the model proves its feasibility to confidently classify middle cerebral artery (MCA) waveforms in near real-time.

Heart failure is a devastating disease that has high mortality rates and a negative impact on quality of life. Heart failure patients often experience emergency readmission after an initial episode, often due to inadequate management. A timely diagnosis and treatment of underlying issues can significantly reduce the risk of emergency readmissions. The purpose of this project was to predict emergency readmissions of discharged heart failure patients using classical machine learning (ML) models based on Electronic Health Record (EHR) data. The dataset used for this study consisted of 166 clinical biomarkers from 2008 patient records. Three feature selection techniques were studied along with 13 classical ML models using five-fold cross-validation. A stacking ML model was trained using the predictions of the three best-performing models for final classification. The stacking ML model provided an accuracy, precision, recall, specificity, F1-score, and area under the curve (AUC) of 89.41%, 90.10%, 89.41%, 87.83%, 89.28%, and 0.881, respectively. This indicates the effectiveness of the proposed model in predicting emergency readmissions. The healthcare providers can intervene pro-actively to reduce emergency hospital readmission risk and improve patient outcomes and decrease healthcare costs using the proposed model.

Electroencephalogram (EEG) signals immensely suffer from several physiological artifacts, including electrooculogram (EOG), electromyogram (EMG), and electrocardiogram (ECG) artifacts, which must be removed to ensure EEG’s usability. This paper proposes a novel one-dimensional convolutional neural network (1D-CNN), i.e., MultiResUNet3+, to denoise physiological artifacts from corrupted EEG. A publicly available dataset containing clean EEG, EOG, and EMG segments is used to generate semi-synthetic noisy EEG to train, validate and test the proposed MultiResUNet3+, along with four other 1D-CNN models (FPN, UNet, MCGUNet, LinkNet). Adopting a five-fold cross-validation technique, all five models’ performance is measured by estimating temporal and spectral percentage reduction in artifacts, temporal and spectral relative root mean squared error, and average power ratio of each of the five EEG bands to whole spectra. The proposed MultiResUNet3+ achieved the highest temporal and spectral percentage reduction of 94.82% and 92.84%, respectively, in EOG artifacts removal from EOG-contaminated EEG. Moreover, compared to the other four 1D-segmentation models, the proposed MultiResUNet3+ eliminated 83.21% of the spectral artifacts from the EMG-corrupted EEG, which is also the highest. In most situations, our proposed model performed better than the other four 1D-CNN models, evident by the computed performance evaluation metrics.

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.

Magnetic resonance imaging (MRI) is commonly used in medical diagnosis and minimally invasive image-guided operations. During an MRI scan, the patient’s electrocardiogram (ECG) may be required for either gating or patient monitoring. However, the challenging environment of an MRI scanner, with its several types of magnetic fields, creates significant distortions of the collected ECG data due to the Magnetohydrodynamic (MHD) effect. These changes can be seen as irregular heartbeats. These distortions and abnormalities hamper the detection of QRS complexes, and a more in-depth diagnosis based on the ECG. This study aims to reliably detect R-peaks in the ECG waveforms in 3 Tesla (T) and 7T magnetic fields. A novel model, Self-Attention MHDNet, is proposed to detect R peaks from the MHD corrupted ECG signal through 1D-segmentation. The proposed model achieves a recall and precision of 99.83% and 99.68%, respectively, for the ECG data acquired in a 3T setting, while 99.87% and 99.78%, respectively, in a 7T setting. This model can thus be used in accurately gating the trigger pulse for the cardiovascular functional MRI.

Common carotid intima-media thickness (CIMT) is a common measure of atherosclerosis, often assessed through carotid ultrasound images. However, the use of deep learning methods for medical image analysis, segmentation and CIMT measurement in these images has not been extensively explored. This study aims to evaluate the performance of four recent deep learning models, including a convolutional neural network (CNN), a self-organizing operational neural network (self-ONN), a transformer-based network and a pixel difference convolution-based network, in segmenting the intima-media complex (IMC) using the CUBS dataset, which includes ultrasound images acquired from both sides of the neck of 1088 participants. The results show that the self-ONN model outperforms the conventional CNN-based model, while the pixel difference- and transformer-based models achieve the best segmentation performance.

Abstract An inductively tuned modified split-ring resonator-based metamaterial (MTM) is presented in this article that provides multiple resonances covering S, C, X, and Ku-bands. The MTM is designed on an FR-4 substrate with a thickness of 1.5 mm and an electrical dimension of 0.063λ × 0.063λ where wavelength, λ is calculated at 2.38 GHz. The resonator part is a combination of three squared copper rings and one circular ring in which all the square rings are modified shaped, and the inner two rings are interconnected. The resonance frequency is tuned by adding inductive metal strips in parallel two vertical splits of the outer ring that causes a significant shift of resonances towards the lower frequencies and a highly effective medium ratio (EMR) of 15.75. Numerical simulation software CST microwave studio is used for the simulation and performance analysis of the proposed unit cell. The MTM unit cell exhibits six resonances of transmission coefficient (S21) at 2.38, 4.24, 5.98, 9.55, 12.1, and 14.34 GHz covering S, C, X, and Ku-bands with epsilon negative (ENG), near-zero permeability, and near-zero refractive index (NZI). The simulated result is validated by experiment with good agreement between them. The performance of the array of the unit cells is also investigated in both simulation and measurement. The equivalent circuit modeling has been accomplished using Advanced Design Software (ADS) that shows a similar S21 response compared to CST simulation. Noteworthy to mention that with the copper backplane, the same unit cell provides multiband absorption properties with four major absorption peaks of 99.6%, 95.7%, 99.9%, 92.7% with quality factors(Q-factor) of 28.4, 34.4, 23, and 32 at 3.98, 5.5, 11.73 and 13.47 GHz, respectively which can be applied for sensing and detecting purposes. The application of an array of the unit cells is investigated using it as a superstrate of an antenna that provides a 73% (average) increase of antenna gain. Due to its simple design, compact dimension with high EMR, ENG property with near-zero permeability, this multiband NZI metamaterial can be used for microwave applications, especially for multiband antenna gain enhancement.

Plants are a major source of food for the world population. Plant diseases contribute to production loss, which can be tackled with continuous monitoring. Manual plant disease monitoring is both laborious and error-prone. Early detection of plant diseases using computer vision and artificial intelligence (AI) can help to reduce the adverse effects of diseases and also overcome the shortcomings of continuous human monitoring. In this work, we propose the use of a deep learning architecture based on a recent convolutional neural network called EfficientNet on 18,161 plain and segmented tomato leaf images to classify tomato diseases. The performance of two segmentation models i.e., U-net and Modified U-net, for the segmentation of leaves is reported. The comparative performance of the models for binary classification (healthy and unhealthy leaves), six-class classification (healthy and various groups of diseased leaves), and ten-class classification (healthy and various types of unhealthy leaves) are also reported. The modified U-net segmentation model showed accuracy, IoU, and Dice score of 98.66%, 98.5%, and 98.73%, respectively, for the segmentation of leaf images. EfficientNet-B7 showed superior performance for the binary classification and six-class classification using segmented images with an accuracy of 99.95% and 99.12%, respectively. Finally, EfficientNet-B4 achieved an accuracy of 99.89% for ten-class classification using segmented images. It can be concluded that all the architectures performed better in classifying the diseases when trained with deeper networks on segmented images. The performance of each of the experimental studies reported in this work outperforms the existing literature.

Abstract In this article, we propose SNG (single negative) metamaterial fabricated on Mg–Zn ferrite-based flexible microwave composites. Firstly, the flexible composites are synthesized by the sol-gel method having four different molecular compositions of MgxZn(1−x)Fe2O4, which are denoted as Mg20, Mg40, Mg60, and Mg80. The structural, morphological, and microwave properties of the synthesized flexible composites are analyzed using X-ray diffraction (XRD), field emission scanning electron microscopy (FESEM), and conventional dielectric assessment kit (DAK) to justify their possible application as dielectric substrate at microwave frequency regime. Thus the average grain size is found from 20 to 24 nm, and the dielectric constants are 6.01, 5.10, 4.19, and 3.28, as well as loss tangents, are 0.002, 0.004, 0.006, and 0.008 for the prepared Mg–Zn ferrites, i.e., Mg20, Mg40, Mg60, and Mg80 respectively. Besides, the prepared low-cost Mg–Zn ferrite composites exhibit high flexibility and lightweight, which makes them a potential candidate as a metamaterial substrate. Furthermore, a single negative (SNG) metamaterial unit cell is fabricated on the prepared, flexible microwave composites, and their essential electromagnetic behaviors are observed. Very good effective medium ratios (EMR) vales are obtained from 14.65 to 18.47, which ensure the compactness of the fabricated prototypes with a physical dimension of 8 × 6.5 mm2 . Also, the proposed materials have shown better performances comparing with conventional FR4 and RO4533 materials, and they have covered S-, C-, X-, Ku-, and K-band of microwave frequency region. Thus, the prepared, flexible SNG metamaterials on MgxZn(1−x)Fe2O4 composites are suitable for microwave and flexible technologies.

Diabetic sensorimotor polyneuropathy (DSPN) is an early indicator for non-healing diabetic wounds and diabetic foot ulcers, which account for one of the most common complications of diabetes, leading to increased healthcare cost, decreased quality of life, infections, amputations, and death. Early detection and intelligent classification tools for DSPN can allow correct diagnosis and treatment of painful diabetic neuropathy as well as a timely intervention to prevent foot ulceration, amputation, and other diabetic complications. Hence, to successfully mitigate the prevalence of DSPN, this study aims to depict an intelligent DSPN severity classifier using Adaptive Neuro Fuzzy Inference System (ANFIS). Michigan Neuropathy Screening Instrumentation (MNSI) was considered as the input for identification and stratification of DSPN. Patients have been classified into four classes: Absent, Mild, Moderate, and Severe. The model accuracy was validated with the results from different machine learning algorithms. The Accuracy, sensitivity, and specificity of the ANFIS model are 91.17±1.18%, 92±2.26%, 96.72±0.93%, respectively. The proposed classifier was used to classify the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trial patients and observed that in the first, eighth, and nineteenth EDIC years 18.31%, 39.45%, and 59.14% patients had different levels of DSPN. This study also investigates the changes in muscle activity during gait from three different lower limb muscles (vastus lateralis (VL), tibialis anterior (TA), and gastrocnemius medialis (GM)) electromyography (EMG) of DSPN patients with different severity levels classified by the proposed classifier and observed that VL and GM muscles show an increase in delay for activation peak and decrease in peak magnitude during gait with the progression of DSPN severity. Based on this observation, the ANFIS model was trained using the extracted EMG features for DSPN severity stratification and showed promising results. Our proposed ANFIS based severity classifier using both MNSI variables and EMG features will help health professionals to diagnose and stratify DSPN severity based on both signs and symptoms and electrophysiological changes due to DSPN.

A non-invasive, low-powered, and portable electromagnetic (EM) head imaging system is presented using metamaterial (MTM) loaded compact directional 3D antenna. The antenna consists of two slotted dipole elements with $2\times 3$ and $3\times 3$ finite MTM array elements in top and ground, respectively, and folded parasitic elements that operate within the frequency range of 1.12 GHz to 2.5 GHz. The MTM array elements are optimized to enhance the overall performance regarding antenna bandwidth, realized gain, efficiency, and directionality in both free space and proximity to the head model. The mathematical modelling is also analyzed to justify the integration of MTM unit cells to the top and ground side of the antenna. The impact of MTM on SAR analysis is also performed. A tissue-mimicking 3D head phantom is fabricated and measured to validate the antenna performance. A nine-antenna portable setup is used with the fabricated phantom to measure and collect the scattering parameters that are later analyzed to detect and reconstruct the haemorrhage images by applying the updated IC-CF-DMAS algorithm. The overall performance demonstrates the feasibility of the proposed system as a portable platform to successfully detect, locate and monitor the haemorrhages inside the head in EM imaging system.

In this paper, the triple reflection band split O circled T (SOCT) shape metamaterial resonator is presented based on the transmission line principle. This paper aims to develop a miniature metamaterial resonator that can simultaneously perform as a reflector and a sensing element in the microwave range. Compare to symmetric and asymmetric structures; the reflection feature is mostly available in a typical resonating structure. The primary motivation beyond the presented work is to achieve high reflection with triple resonance points at 5.8 GHz, 6.37 GHz and 6.57 GHz. The proposed structure achieved Double Negative (DNG) features on this particular resonance with a relative permittivity value ranges −2.17 to −6.62 and relative permeability of −0.73 to −4.15. The scattering parameter performance was verified through simulation and measurement for unit cell and $5\times 8$ array structure. An analytical sensing ability for liquid salinity was performed for potential microwave application, which indicates a potential outcome of the proposed structure in microwave sensing applications.

This paper presents the detection of brain tumors through the YOLOv3 deep neural network model in a portable electromagnetic (EM) imaging system. YOLOv3 is a popular object detection model with high accuracy and improved computational speed. Initially, the scattering parameters are collected from the nine-antenna array setup with a tissue-mimicking head phantom, where one antenna acts as a transmitter and the other eight antennas act as receivers. The images are then reconstructed from the post-processed scattering parameters by applying the modified delay-multiply-and-sum algorithm that contains $416\times 416$ pixels. Fifty sample images are collected from the different head regions through the EM imaging system. The images are later augmented to generate a final image data set for training, validation, and testing, where the data set contains 1000 images, including fifty samples with a single and double tumor. 80% of the images are utilized for training the network, whereas 10% are used for validation, and the rest 10% are utilized for testing purposes. The detection performance is investigated with the different image data sets. The achieved detection accuracy and F1 scores are 95.62% and 94.50%, respectively, which ensure better detection accuracy. The training accuracy and validation losses are 96.74% and 9.21%, respectively. The tumor detection with its location in different cases from the testing images is evaluated through YOLOv3, which demonstrates its potential in the portable electromagnetic head imaging system.

Electroencephalography (EEG) based biometric systems are gaining attention for their anti-spoofing capability but lack accuracy due to signal variability at different psychological and physiological conditions. On the other hand, keystroke dynamics-based systems achieve very high accuracy but have low anti-spoofing capability. To address these issues, a novel multimodal biometric system combining EEG and keystroke dynamics is proposed in this paper. A dataset was created by acquiring both keystroke dynamics and EEG signals simultaneously from 10 users. Each user participated in 500 trials at 10 different sessions (days) to replicate real-life signal variability. A machine learning classification pipeline is developed using multi-domain feature extraction (time, frequency, time-frequency), feature selection (Gini impurity), classifier design, and score level fusion. Different classifiers were trained, validated, and tested for two different classification experiments – personalized and generalized. For identification and authentication, 99.9% and 99.6% accuracies are achieved, respectively for the Random Forest classifier in 5 fold cross-validation. These results outperform the individual modalities with a significant margin (~5%). We also developed a binary template matching-based algorithm, which gives 93.64% accuracy 6X faster. The proposed method can be considered secure and reliable for any kind of biometric identification and authentication.