Trustworthy deep learning framework for the detection of abnormalities in X-ray shoulder images.

Musculoskeletal conditions affect an estimated 1.7 billion people worldwide, causing intense pain and disability. These conditions lead to 30 million emergency room visits yearly, and the numbers are only increasing. However, diagnosing musculoskeletal issues can be challenging, especially in emergencies where quick decisions are necessary. Deep learning (DL) has shown promise in various medical applications. However, previous methods had poor performance and a lack of transparency in detecting shoulder abnormalities on X-ray images due to a lack of training data and better representation of features. This often resulted in overfitting, poor generalisation, and potential bias in decision-making. To address these issues, a new trustworthy DL framework has been proposed to detect shoulder abnormalities (such as fractures, deformities, and arthritis) using X-ray images. The framework consists of two parts: same-domain transfer learning (TL) to mitigate imageNet mismatch and feature fusion to reduce error rates and improve trust in the final result. Same-domain TL involves training pre-trained models on a large number of labelled X-ray images from various body parts and fine-tuning them on the target dataset of shoulder X-ray images. Feature fusion combines the extracted features with seven DL models to train several ML classifiers. The proposed framework achieved an excellent accuracy rate of 99.2%, F1Score of 99.2%, and Cohen's kappa of 98.5%. Furthermore, the accuracy of the results was validated using three visualisation tools, including gradient-based class activation heat map (Grad CAM), activation visualisation, and locally interpretable model-independent explanations (LIME). The proposed framework outperformed previous DL methods and three orthopaedic surgeons invited to classify the test set, who obtained an average accuracy of 79.1%. The proposed framework has proven effective and robust, improving generalisation and increasing trust in the final results.

Clinical electromagnetic brain scanner.

Stroke is a leading cause of death and disability worldwide, and early diagnosis and prompt medical intervention are thus crucial. Frequent monitoring of stroke patients is also essential to assess treatment efficacy and detect complications earlier. While computed tomography (CT) and magnetic resonance imaging (MRI) are commonly used for stroke diagnosis, they cannot be easily used onsite, nor for frequent monitoring purposes. To meet those requirements, an electromagnetic imaging (EMI) device, which is portable, non-invasive, and non-ionizing, has been developed. It uses a headset with an antenna array that irradiates the head with a safe low-frequency EM field and captures scattered fields to map the brain using a complementary set of physics-based and data-driven algorithms, enabling quasi-real-time detection, two-dimensional localization, and classification of strokes. This study reports clinical findings from the first time the device was used on stroke patients. The clinical results on 50 patients indicate achieving an overall accuracy of 98% in classification and 80% in two-dimensional quadrant localization. With its lightweight design and potential for use by a single para-medical staff at the point of care, the device can be used in intensive care units, emergency departments, and by paramedics for onsite diagnosis.

Wide-Angle Beam Steering Closed-Form Pillbox Antenna Fed by Substrate-Integrated Waveguide Horn for On-the-Move Satellite Communications.

Wide-angle mechanical beam steering for on-the-move satellite communications is presented in this paper based on a closed-form pillbox antenna system. It includes three main parts: a fixed-feed part, which is a substrate-integrated waveguide (SIW) horn with an extended aperture attached to a parabolic reflector; a novel quasi-optical system, which is a single coupling slot alongside and without spacing from the parabolic reflector; and a radiating disc, which is a leaky-wave metallic pattern. To make the antenna compact, pillbox-based feeding is implemented underneath the metallic patterns. The antenna is designed based on a substrate-guided grounded concept using leaky-wave metallic patterns operating at 20 GHz. Beam scanning is achieved using mechanical rotation of the leaky-wave metallic patterns. The proposed antenna has an overall size of 340 × 335 × 2 mm3, a gain of 23.2 dBi, wide beam scanning range of 120°, from -60° to +60° in the azimuthal plane, and a low side lobe level of -17.8 dB at a maximum scan angle of 60°. The proposed antenna terminal is suitable for next-generation ubiquitous connectivity for households and small businesses in remote areas, ships, unmanned aerial vehicles, and disaster management.

Shielded Cone Coil Array for Non-Invasive Deep Brain Magnetic Stimulation.

Non-invasive deep brain stimulation using transcranial magnetic stimulation is a promising technique for treating several neurological disorders, such as Alzheimer's and Parkinson's diseases. However, the currently used coils do not demonstrate the required stimulation performance in deep regions of the brain, such as the hippocampus, due to the rapid decay of the field inside the head. This study proposes an array that uses the cone coil method for deep stimulation. This study investigates the impact of magnetic core and shielding on field strength, focality, decay rate, and safety. The coil's size and shape effects on the electric field distribution in deep brain areas are also examined. The finite element method is used to calculate the induced electric field in a realistic human head model. The simulation results indicate that the magnetic core and shielding increase the electric field intensity and enhance focality but do not improve the field decay rate. However, the decay rate can be reduced by increasing the coil size at the expense of focality. By adopting an optimum cone structure, the proposed five-coil array reduces the electric field attenuation rate to reach the stimulation threshold in deep regions while keeping all other regions within safety limits. In vitro and in vivo experimental results using a head phantom and a dead pig's head validate the simulated results and confirm that the proposed design is a reliable and efficient candidate for non-invasive deep brain magnetic stimulation.

Benign and Malignant Skin Lesions: Dielectric Characterization, Modelling and Analysis in Frequency Band 1 to 14 GHz.

OBJECTIVE: This paper aims to characterize Non-Melanoma malignancies and their corresponding benign conditions in ex-vivo/in-vivo tissue environments to study the feasibility of microwave techniques for skin cancer detection. METHODS: The dielectric dataset is developed across the frequency band 1 to 14 GHz using Keysight slim-form and RG405 probe characterization systems. The acquired reflection data captured by the systems is converted to dielectric values using the Open-Water-Short and Open-Water-Liquid calibration methods, respectively. Furthermore, the impact of anaesthesia application during skin excision procedure on ex-vivo dielectric data is investigated. RESULTS: The observations suggest that the dielectric properties (DPs) of excised skin lesions may not accurately represent actual tissue properties as they vary significantly (Dielectric Constant Contrast = 30.7%, Loss-Factor Contrast = 66.6%) compared to pre-excision conditions. In-vivo dielectric data analysis indicates that when compared to healthy skin, malignant Basal Cell Carcinoma presents increased DPs (dielectric constant & loss factor) of (24.8 & 38.6 %), respectively. On the other hand, for malignant Squamous Cell Carcinoma and pre-malignant Actinic Keratosis, the measured results show decreased DPs (dielectric constant & loss factor) accordingly by (19.4 & 18.2 %) and (19.2 & 27.9 %). The corresponding benign lesions have less than 13 % dielectric contrast compared to healthy skin across the tested band. CONCLUSION: The significant contrasts between in-vivo healthy and cancerous skin DPs strongly suggest the viability of the microwave band for skin cancer detection. SIGNIFICANCE: The research finding of this study would be critical in developing a portable electromagnetic system for skin cancer detection.

Training Universal Deep-Learning Networks for Electromagnetic Medical Imaging Using a Large Database of Randomized Objects.

Deep learning has become a powerful tool for solving inverse problems in electromagnetic medical imaging. However, contemporary deep-learning-based approaches are susceptible to inaccuracies stemming from inadequate training datasets, primarily consisting of signals generated from simplified and homogeneous imaging scenarios. This paper introduces a novel methodology to construct an expansive and diverse database encompassing domains featuring randomly shaped structures with electrical properties representative of healthy and abnormal tissues. The core objective of this database is to enable the training of universal deep-learning techniques for permittivity profile reconstruction in complex electromagnetic medical imaging domains. The constructed database contains 25,000 unique objects created by superimposing from 6 to 24 randomly sized ellipses and polygons with varying electrical attributes. Introducing randomness in the database enhances training, allowing the neural network to achieve universality while reducing the risk of overfitting. The representative signals in the database are generated using an array of antennas that irradiate the imaging domain and capture scattered signals. A custom-designed U-net is trained by using those signals to generate the permittivity profile of the defined imaging domain. To assess the database and confirm the universality of the trained network, three distinct testing datasets with diverse objects are imaged using the designed U-net. Quantitative assessments of the generated images show promising results, with structural similarity scores consistently exceeding 0.84, normalized root mean square errors remaining below 14%, and peak signal-to-noise ratios exceeding 33 dB. These results demonstrate the practicality of the constructed database for training deep learning networks that have generalization capabilities in solving inverse problems in medical imaging without the need for additional physical assistant algorithms.

Combating Coronavirus Using Resonant Electromagnetic Irradiation.

The interaction of electromagnetic (EM) waves with the COVID-19 virus is studied to define the frequencies that cause maximum energy absorption by the virus and the power level needed to cause a lethal temperature rise. The full-wave EM simulator is used to model the virus and study the effects of its size and dielectric properties on the absorbed power across a wide range of frequencies. The results confirm potential resonance conditions, where specific frequencies produce maximum absorption and subsequent temperature rise that can destroy the virus. Furthermore, the study confirms that maximum power deposition in the virus occurs at specific wavelengths depending on its size. Also, the simulation is used to find the power required to destroy the virus and determine the total power required to destroy it in an oral activity, such as coughing, made by infected individuals. Furthermore, the study explained why irradiation by UV-C band is effective to decrease virus activity or even eradicate it.

Wearable Dual Polarized Electromagnetic Knee Imaging System.

With the increasing uptake of sport activities, onsite detection of associated knee injuries at early stages is in high demand to avoid severe ligament tear and long treatment period. Portable electromagnetic imaging (EMI) systems have the potential to meet that demand, but there are challenges. For example, EMI is based on the contrast in the dielectric properties due to the accumulated fluid after knee injury. However, that fluid can be in any shape and orientation. Therefore, to capture enough data for processing, EMI should operate as a dual-polarized wearable system with compact antennas. Thus, the proposed system is a textile brace worn on the knee and consists of an 8-element dual-polarized aperture antenna array, which is matched with the knee. Each of the utilized antennas is fed by two orthogonal coaxial feed, occupies a small size of 36 ×36 ×3.1 mm3, and is backed by a full ground plane for unidirectional radiation. The antenna covers the band 0.7-3.3 GHz (130%), with front to back ratio of more than 10 dB. The textile wool-felt is used as the substrate to enable building flexible brace system. The system's capability to reconstruct knee images with different injuries is verified on realistic knee models and phantoms. The double stage delay, multiply and sum algorithm (DS-DMAS) is used to reconstruct those images, which demonstrate the efficiency of the dual-polarized system and its superiority over single-polarized systems.

Feasibility of Electromagnetic Knee Imaging Verified on Ex-Vivo Pig Knees.

OBJECTIVE: The potential of electromagnetic knee imaging system verified on ex-vivo pig knee joint as an essential step before clinical trials is demonstrated. The system, which includes an antenna array of eight printed biconical elements operating at the band 0.7-2.2 GHz, is portable and cost-effective. Importantly, it can provide daily monitoring and onsite real-time examinations imaging tool for knee injuries. METHODS: Six healthy hind legs from three dead adult pigs were removed at the hip and suspended in the developed system. For each pig, the right- and left-knee were scanning sequentially. Then ligament tear was emulated by injecting distilled water into the left knee joint of each pig for early (5 mL water) and mid-stage (10 mL water) injuries. The injured left knees were re-scanned. A modified multi-static fast delay, multiply and sum algorithm (MS-FDMAS) is used to reconstruct imaging of the knee. All knee's connective tissues, such as anterior and posterior cruciate ligaments (ACL, PCL), lateral and medial collateral ligaments (LCL, MCL), tendons, and meniscus, are extracted from a healthy hind leg along with collected synovial fluid. The extracted tissues and fluid were characterized and modelled as their data are not available in the literature, then imported to build an equivalent model for pig knee of 1 mm3 resolution in a realistic simulation environment. RESULTS: The obtained results proved potential of the proposed system to detect ligament/tendon tears. CONCLUSION: The proposed system has the potential to detect early knee injuries in a realistic environment. SIGNIFICANCE: Contactless EM knee imaging system verified on ex-vivo pig joints confirms its potential to reconstruct knee images. This work lays the groundwork for clinical EM system for detecting and monitoring knee injuries. (EM).

Adaptive Clustering Distorted Born Iterative Method for Microwave Brain Tomography With Stroke Detection and Classification.

A modified distorted Born iterative method (DBIM), which includes clustering of reconstructed electrical properties (EPs) after certain iterations, is presented for brain imaging aiming at stroke detection and classification. For this approach to work, a rough estimation of number of different materials (or bio-tissues) in the imaged domain and their corresponding rough dielectric properties (permittivity and conductivity) are needed as a prior information. The proposed adaptive clustering DBIM (AC-DBIM) is compared with three conventional methods (DBIM, multiplicative regularized contrast source inversion (MR-CSI), and CSI for shape and location reconstruction (SL-CSI)) in two-dimensional scenario on a head phantom and numerical head model with different strokes. Three-dimensional simulations are also conducted to indicate the suitability of AC-DBIM in real-life brain imaging. Lastly, the proposed algorithm is assessed using a clinical electromagnetic head scanner developed on phantoms. The simulation and experimental results show superiority of AC-DBIM compared to conventional methods. AC-DBIM achieves significant improvement in the size and shape reconstruction and reduction in errors and standard deviation of the reconstructed εr and σ at clinical scenarios compared with conventional DBIM.

Case Report: Preliminary Images From an Electromagnetic Portable Brain Scanner for Diagnosis and Monitoring of Acute Stroke.

Introduction: Electromagnetic imaging is an emerging technology which promises to provide a mobile, and rapid neuroimaging modality for pre-hospital and bedside evaluation of stroke patients based on the dielectric properties of the tissue. It is now possible due to technological advancements in materials, antennae design and manufacture, rapid portable computing power and network analyses and development of processing algorithms for image reconstruction. The purpose of this report is to introduce images from a novel, portable electromagnetic scanner being trialed for bedside and mobile imaging of ischaemic and haemorrhagic stroke. Methods: A prospective convenience study enrolled patients (January 2020 to August 2020) with known stroke to have brain electromagnetic imaging, in addition to usual imaging and medical care. The images are obtained by processing signals from encircling transceiver antennae which emit and detect low energy signals in the microwave frequency spectrum between 0.5 and 2.0 GHz. The purpose of the study was to refine the imaging algorithms. Results: Examples are presented of haemorrhagic and ischaemic stroke and comparison is made with CT, perfusion and MRI T2 FAIR sequence images. Conclusion: Due to speed of imaging, size and mobility of the device and negligible environmental risks, development of electromagnetic scanning scanner provides a promising additional modality for mobile and bedside neuroimaging.

Textile Electromagnetic Brace for Knee Imaging.

A wearable textile brace is introduced as an electromagnetic imaging system that breaks hospital boundaries to real-time onsite scanning for knee injuries. The proposed brace consists of a 12-element textile slot loop antenna array, which is designed to match the human knee for enhanced electromagnetic wave penetration. Wool felt and conductive fabric are used to fabricate the antenna array thanks to their flexibility and proper dielectric properties. Each antenna element has a compact footprint of 42 ×24 ×3.22 mm3 and achieves unidirectional radiation, high front-to-back ratio of 14 dB, wide bandwidth of 81% at 0.7-1.7 GHz, and safe SAR levels. A modified double-stage delay, multiply, and sum (DS-DMAS) algorithm is used to process the collected signals from the antenna array based on differential left/right knee imaging. The reconstructed images numerically and experimentally on realistic phantoms demonstrate the potential of the brace system for onsite detection of different types of ligaments/tendon tears.

Flexible Electromagnetic Cap for Three-Dimensional Electromagnetic Head Imaging.

The timely treatment is the crucial element for the survival of patients with brain stroke. Thus, a fast, cost-effective, and portable device is needed for the early and on-the-spot diagnosis of stroke patients. A 3D electromagnetic head imaging system for rapid brain stroke diagnosis with a wearable and lightweight platform is presented. The platform comprises a custom-built flexible cap with a 24-element planar antenna array, and a flexible matching medium layer. The custom-built cap is made out of an engineered polymer-ceramic composite substrate of RTV silicone rubber and aluminum oxide (Al2O3) for enhanced dielectric properties and mechanical flexibility and robustness. The array is arranged into two elliptical rings that are entirely incorporated into the flexible cap. The employed antenna elements within the system are compact with low SAR values over the utilized frequency range of 0.9-2.5 GHz. Moreover, a flexible matching medium layer is introduced on the front of the apertures of the antenna array to enhance the impedance matching with the skin. The detection capability of the system is experimentally verified on 3D realistic head phantoms at multiple imaging scenarios and different types of strokes. The reconstructed 3D and 2D multi-slice images using the beamforming and polar sensitivity encoding (PSE) image processing algorithms indicate the applicability and potential of the system for onsite brain imaging.

Electromagnetic Torso Scanning: A Review of Devices, Algorithms, and Systems.

The past decade has witnessed a surge into research on disruptive technologies that either challenge or complement conventional thoracic diagnostic modalities. The non-ionizing, non-invasive, compact, and low power requirements of electromagnetic (EM) techniques make them among the top contenders with varieties of proposed scanning systems, which can be used to detect wide range of thoracic illnesses. Different configurations, antenna topologies and detection or imaging algorithms are utilized in these systems. Hence, to appreciate their progress and assess their potential, a critical review of EM thoracic scanning systems is presented. Considering the numerous thoracic diseases, such as fatty liver disease, lung cancer, respiratory and heart related complications, this paper will exclusively focus on torso scanning systems, tracing the early foundation of research that studied the possibility of using EM waves to detect thoracic diseases besides exploring recent progresses. The advantages and disadvantages of proposed systems and future possibilities are thoroughly discussed.

Flexible Electromagnetic Cap for Head Imaging.

A wideband wearable electromagnetic (EM) head imaging system for brain stroke detection is presented. The proposed system aims at overcoming the challenges of size, rigidity, and complex structures of existing systems. The proposed system is built into a light-weight and compact imaging platform, which integrates a 16-element antenna array into a highly flexible custom-made wearable cap made of a cost-effective and robust room-temperature-vulcanizing (RTV) silicone. The system mitigates the mismatch between the skin and antenna array by introducing a flexible high-permittivity matching layer. The utilized compact antenna demonstrates wideband operational frequency over 0.6-2.5 GHz with a low signal distortion, safe values of SAR, and unidirectional radiations. The system is experimentally validated on realistic head phantoms. The polar sensitivity encoding (PSE) image processing algorithm is utilized to generate 2D images of different testing scenarios. The obtained images of a stroke-like target inside the head phantoms demonstrate the merits and feasibility of the system for preclinical trials.

Implantable Sensor for Detecting Changes in the Loss Tangent of Cerebrospinal Fluid.

The increasing utilization of cerebrospinal fluid (CSF) in early detection of Alzheimer's disease (AD) is attributed to the change of Amyloid- ß proteins. Since, the brain is suspended in CSF, changes of Amyloid- ß proteins in CSF reflect a pathophysiological variation of the brain due to AD. However, the correlation between Amyloid- ß proteins and the dielectric properties (DPs) of CSF is still an open question. This paper reports the characterized DPs of CSF collected from canines using lumbar punctures. The CSF samples from canines show a strong correlation with respect to human in terms of the loss tangent, which indicates suitability of using canines as translational primates. Amyloid- ß [ Aß(1-40) and Aß(1-42)] proteins associated with AD were added to CSF samples in order to emulate AD condition. The results of emulated AD condition suggest a decrease in the relative permittivity and increase in the loss tangent. To detect changes in the loss tangent of CSF, which combines both relative permittivity and conductivity, a developed sensor is proposed. The designed sensor consists of a voltage controlled oscillator (VCO) and implantable antenna, which exhibits a wideband and low quality factor to be stable with respect to changes in the loss tangent of CSF. The measurements of the received power levels from the sensor in different liquid-based phantoms having different loss tangent values were used to correlate changes in the loss tangent. The developed correlation model is able to predict the loss tangent based on the received power level, which can be used to detect changes in the loss tangent of CSF due to AD. Consequently, this approach could be used as an early diagnosis of AD.

Millimeter-Wave Substrate Integrated Waveguide Probe for Skin Cancer Detection.

This article presents an efficient and low-cost near-field probe, designed for early-stage skin cancer detection. Thanks to a tapered section, the device can achieve a sharp concentration of electric field at its tip. Moreover, the adoption of substrate integrated waveguide (SIW) technology ensures an easy and cheap fabrication process. The probe is realized on a high dielectric constant substrate (Rogers RO3210) that provides a good impedance matching with the skin, thus allowing to use the device in direct contact with it. This feature is essential to ensure that the proposed system can be adopted as a practical and effective tool for a fast scanning of many suspected skin regions. The probe is designed to operate at around 40 GHz in order to achieve the penetration depth required to detect small cancer lumps in the skin, while preventing the fields from interacting with the underlying biological tissues. Furthermore, the concept of detection depth is defined with the goal of introducing a metric that is more suitable than the penetration depth to express the notion of the maximum distance from the skin surface at which a tumor can be detected. Thanks to a differential imaging algorithm, the probe is capable of working on every different skin types and body region. The proposed device has a lateral sensitivity and detection depth of 0.2 and 0.55 mm respectively. The probe was designed and tested through simulations in CST Microwave Studio, as well as fabricated and validated through measurements on an artificial human skin phantom.

Electromagnetic Medical Sensing.

In recent years, electromagnetic (EM) techniques have been widely investigated and researched for different medical applications, from early diagnosis to therapy and monitoring [...].

Three-Dimensional Electromagnetic Torso Scanner.

A three-dimensional (3D) electromagnetic torso scanner system is presented. This system aims at providing a complimentary/auxiliary imaging modality to supplement conventional imaging devices, e.g., ultrasound, computerized tomography (CT) and magnetic resonance imaging (MRI), for pathologies in the chest and upper abdomen such as pulmonary abscess, fatty liver disease and renal cancer. The system is comprised of an array of 14 resonance-based reflector (RBR) antennas that operate from 0.83 to 1.9 GHz and are located on a movable flange. The system is able to scan different regions of the chest and upper abdomen by mechanically moving the antenna array to different positions along the long axis of the thorax with an accuracy of about 1 mm at each step. To verify the capability of the system, a three-dimensional imaging algorithm is proposed. This algorithm utilizes a fast frequency-based microwave imaging method in conjunction with a slice interpolation technique to generate three-dimensional images. To validate the system, pulmonary abscess was simulated within an artificial torso phantom. This was achieved by injecting an arbitrary amount of fluid (e.g., 30 mL of water), into the lungs regions of the torso phantom. The system could reliably and reproducibly determine the location and volume of the embedded target.

The Progress of Glucose Monitoring-A Review of Invasive to Minimally and Non-Invasive Techniques, Devices and Sensors.

Current glucose monitoring methods for the ever-increasing number of diabetic people around the world are invasive, painful, time-consuming, and a constant burden for the household budget. The non-invasive glucose monitoring technology overcomes these limitations, for which this topic is significantly being researched and represents an exciting and highly sought after market for many companies. This review aims to offer an up-to-date report on the leading technologies for non-invasive (NI) and minimally-invasive (MI) glucose monitoring sensors, devices currently available in the market, regulatory framework for accuracy assessment, new approaches currently under study by representative groups and developers, and algorithm types for signal enhancement and value prediction. The review also discusses the future trend of glucose detection by analyzing the usage of the different bands in the electromagnetic spectrum. The review concludes that the adoption and use of new technologies for glucose detection is unavoidable and closer to become a reality.