Stroke Classification with Microwave Signals using Explainable Wavelet Convolutional Neural Network.

Stroke is one of the leading causes of death and disability. To address this challenge, microwave imaging has been proposed as a portable medical imaging modality. However, accurate stroke classification using microwave signals is still an open challenge. In addition, identified features of microwave signals used for stroke classification need to be linked back to the original data. This work attempts to address these issues by proposing a wavelet convolutional neural network (CNN), which combines multiresolution analysis and CNN to learn distinctive patterns in the scalogram for accurate classification. A game theoretic approach is used to explain the model and indicate distinctive features for discriminating stroke types. The proposed algorithm is tested in simulation and experiments. Different types of noise and manufacturing tolerances are modeled using data collected from healthy human trials and added to the simulation data to bridge the gap between the simulation and real-life data. The achieved classification accuracy using the proposed method ranges from 81.7% for 3D simulations to 95.7% for lab experiments using simple head phantoms. Obtained explanations using the method indicate the relevance of wavelet coefficients on frequencies 0.95-1.45 GHz and the time slot of 1.3 to 1.7 ns for distinguishing ischemic from hemorrhagic strokes.

Novel Microwave Torso Scanner for Thoracic Fluid Accumulation Diagnosis and Monitoring.

Thoracic fluid accumulation is one of the significant and early-stage manifestations of fatal diseases, such as lung-cancer, liver-failure and congestive heart-failure. Currently, computational-tomography (CT)-Scan is the most widely used tool for the detection of thoracic fluid. Yet, it is unable to detect small amounts of fluid, has ionizing radiation and lacks mobility. On the other hand, microwave imaging systems have emerged as an accurate and portable complementary diagnostic tool. However, there is a lack of a complete clinical platform that can fulfill the requirements of accurate and reliable imaging. Therefore, a microwave torso scanner that is designed to meet those requirements is presented. In this system, two elliptical-arrays of microwave antennas (sensors) transmit signals towards the torso and collect the back-scattered signals. The captured signals are then processed by a frequency-based imaging algorithm to form microwave images that display a possible accumulated fluid. The system successfully detects and localized small volumes (3 mL) of fluid injected at different places inside a torso-phantom. As preparations for future clinical trials, the system is tested on healthy subjects to define the threshold range of healthy scenario images.

On-site Rapid Diagnosis of Intracranial Hematoma using Portable Multi-slice Microwave Imaging System.

Rapid, on-the-spot diagnostic and monitoring systems are vital for the survival of patients with intracranial hematoma, as their conditions drastically deteriorate with time. To address the limited accessibility, high costs and static structure of currently used MRI and CT scanners, a portable non-invasive multi-slice microwave imaging system is presented for accurate 3D localization of hematoma inside human head. This diagnostic system provides fast data acquisition and imaging compared to the existing systems by means of a compact array of low-profile, unidirectional antennas with wideband operation. The 3D printed low-cost and portable system can be installed in an ambulance for rapid on-site diagnosis by paramedics. In this paper, the multi-slice head imaging system's operating principle is numerically analysed and experimentally validated on realistic head phantoms. Quantitative analyses demonstrate that the multi-slice head imaging system is able to generate better quality reconstructed images providing 70% higher average signal to clutter ratio, 25% enhanced maximum signal to clutter ratio and with around 60% hematoma target localization compared to the previous head imaging systems. Nevertheless, numerical and experimental results demonstrate that previous reported 2D imaging systems are vulnerable to localization error, which is overcome in the presented multi-slice 3D imaging system. The non-ionizing system, which uses safe levels of very low microwave power, is also tested on human subjects. Results of realistic phantom and subjects demonstrate the feasibility of the system in future preclinical trials.

Design and Experimental Evaluation of a Non-Invasive Microwave Head Imaging System for Intracranial Haemorrhage Detection.

An intracranial haemorrhage is a life threatening medical emergency, yet only a fraction of the patients receive treatment in time, primarily due to the transport delay in accessing diagnostic equipment in hospitals such as Magnetic Resonance Imaging or Computed Tomography. A mono-static microwave head imaging system that can be carried in an ambulance for the detection and localization of intracranial haemorrhage is presented. The system employs a single ultra-wideband antenna as sensing element to transmit signals in low microwave frequencies towards the head and capture backscattered signals. The compact and low-profile antenna provides stable directional radiation patterns over the operating bandwidth in both near and far-fields. Numerical analysis of the head imaging system with a realistic head model in various situations is performed to realize the scattering mechanism of haemorrhage. A modified delay-and-summation back-projection algorithm, which includes effects of surface waves and a distance-dependent effective permittivity model, is proposed for signal and image post-processing. The efficacy of the automated head imaging system is evaluated using a 3D-printed human head phantom with frequency dispersive dielectric properties including emulated haemorrhages with different sizes located at different depths. Scattered signals are acquired with a compact transceiver in a mono-static circular scanning profile. The reconstructed images demonstrate that the system is capable of detecting haemorrhages as small as 1 cm3. While quantitative analyses reveal that the quality of images gradually degrades with the increase of the haemorrhage's depth due to the reduction of signal penetration inside the head; rigorous statistical analysis suggests that substantial improvement in image quality can be obtained by increasing the data samples collected around the head. The proposed head imaging prototype along with the processing algorithm demonstrates its feasibility for potential use in ambulances as an effective and low cost diagnostic tool to assure timely triaging of intracranial hemorrhage patients.

Portable Wideband Microwave Imaging System for Intracranial Hemorrhage Detection Using Improved Back-projection Algorithm with Model of Effective Head Permittivity.

Intracranial hemorrhage is a medical emergency that requires rapid detection and medication to restrict any brain damage to minimal. Here, an effective wideband microwave head imaging system for on-the-spot detection of intracranial hemorrhage is presented. The operation of the system relies on the dielectric contrast between healthy brain tissues and a hemorrhage that causes a strong microwave scattering. The system uses a compact sensing antenna, which has an ultra-wideband operation with directional radiation, and a portable, compact microwave transceiver for signal transmission and data acquisition. The collected data is processed to create a clear image of the brain using an improved back projection algorithm, which is based on a novel effective head permittivity model. The system is verified in realistic simulation and experimental environments using anatomically and electrically realistic human head phantoms. Quantitative and qualitative comparisons between the images from the proposed and existing algorithms demonstrate significant improvements in detection and localization accuracy. The radiation and thermal safety of the system are examined and verified. Initial human tests are conducted on healthy subjects with different head sizes. The reconstructed images are statistically analyzed and absence of false positive results indicate the efficacy of the proposed system in future preclinical trials.

Feasibility of Using Wideband Microwave System for Non-Invasive Detection and Monitoring of Pulmonary Oedema.

Pulmonary oedema is a common manifestation of various fatal diseases that can be caused by cardiac or non-cardiac syndromes. The accumulated fluid has a considerably higher dielectric constant compared to lungs' tissues, and can thus be detected using microwave techniques. Therefore, a non-invasive microwave system for the early detection of pulmonary oedema is presented. It employs a platform in the form of foam-based bed that contains two linear arrays of wideband antennas covering the band 0.7-1 GHz. The platform is designed such that during the tests, the subject lays on the bed with the back of the torso facing the antenna arrays. The antennas are controlled using a switching network that is connected to a compact network analyzer. A novel frequency-based imaging algorithm is used to process the recorded signals and generate an image of the torso showing any accumulated fluids in the lungs. The system is verified on an artificial torso phantom, and animal organs. As a feasibility study, preclinical tests are conducted on healthy subjects to determinate the type of obtained images, the statistics and threshold levels of their intensity to differentiate between healthy and unhealthy subjects.