3D Simulations of Intracerebral Hemorrhage Detection Using Broadband Microwave Technology

Microwave Angiography by Ultra-Wideband Sounding: A Preliminary Investigation

Angiography is a very informative method for physicians such as cardiologists, neurologists and neuroscientists. The current modalities experience some shortages, e.g., ultrasound is very operator dependent. The computerized tomography (CT) and magnetic resonance (MR) angiography are very expensive and near infrared spectroscopy cannot capture the deep arteries. Microwave technology has the potential to address some of these issues while compromising between operator dependency, cost, speed, penetration depth and resolution. This paper studies the feasibility of microwave signals for monitoring of arteries. To this aim, a homogenous phantom mimicking body tissue is built. Four elastic tubes simulate arteries and a mechanical system creates pulsations in these arteries. A multiple input multiple output (MIMO) array of ultra-wideband (UWB) transmitters and receivers illuminates the phantom and captures the reflected signals over the desired observation time period. Since we are only interested in the imaging of dynamic parts, i.e., arteries, the static clutters can be suppressed easily by background subtraction method. To obtain a fast image of arteries, which are pulsating with the heartbeat rate, we calculate the Fourier transform of each channel of the MIMO system over the observation time and apply delay and sum (DAS) beamforming method on the heartbeat rate aligned spectral component. The results show that the lateral and longitudinal images and motion mode (M-mode) time series of different points of phantom have the potential to be used for diagnosis.

On the Role of Training Data for SVM-Based Microwave Brain Stroke Detection and Classification

The aim of this work was to test microwave brain stroke detection and classification using support vector machines (SVMs). We tested how the nature and variability of training data and system parameters impact the achieved classification accuracy. Using experimentally verified numerical models, a large database of synthetic training and test data was created. The models consist of an antenna array surrounding reconfigurable geometrically and dielectrically realistic human head phantoms with virtually inserted strokes of arbitrary size, and different dielectric parameters in different positions. The generated synthetic data sets were used to test four different hypotheses, regarding the appropriate parameters of the training dataset, the appropriate frequency range and the number of frequency points, as well as the level of subject variability to reach the highest SVM classification accuracy. The results indicate that the SVM algorithm is able to detect the presence of the stroke and classify it (i.e., ischemic or hemorrhagic) even when trained with single-frequency data. Moreover, it is shown that data of subjects with smaller strokes appear to be the most suitable for training accurate SVM predictors with high generalization capabilities. Finally, the datasets created for this study are made available to the community for testing and developing their own algorithms.

Artificial Intelligence: A Shifting Paradigm in Cardio-Cerebrovascular Medicine

The future of healthcare is an organic blend of technology, innovation, and human connection. As artificial intelligence (AI) is gradually becoming a go-to technology in healthcare to improve efficiency and outcomes, we must understand our limitations. We should realize that our goal is not only to provide faster and more efficient care, but also to deliver an integrated solution to ensure that the care is fair and not biased to a group of sub-population. In this context, the field of cardio-cerebrovascular diseases, which encompasses a wide range of conditions-from heart failure to stroke-has made some advances to provide assistive tools to care providers. This article aimed to provide an overall thematic review of recent development focusing on various AI applications in cardio-cerebrovascular diseases to identify gaps and potential areas of improvement. If well designed, technological engines have the potential to improve healthcare access and equitability while reducing overall costs, diagnostic errors, and disparity in a system that affects patients and providers and strives for efficiency.

A wearable microwave instrument can detect and monitor traumatic abdominal injuries in a porcine model

Abdominal injury is a frequent cause of death for trauma patients, and early recognition is essential to limit fatalities. There is a need for a wearable sensor system for prehospital settings that can detect and monitor bleeding in the abdomen (hemoperitoneum). This study evaluates the potential for microwave technology to fill that gap. A simple prototype of a wearable microwave sensor was constructed using eight antennas. A realistic porcine model of hemoperitoneum was developed using anesthetized pigs. Ten animals were measured at healthy state and at two sizes of bleeding. Statistical tests and a machine learning method were used to evaluate blood detection sensitivity. All subjects presented similar changes due to accumulation of blood, which dampened the microwave signal (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p < 0.05$$\end{document}p<0.05). The machine learning analysis yielded an area under the receiver operating characteristic (ROC) curve (AUC) of 0.93, showing 100% sensitivity at 90% specificity. Large inter-individual variability of the healthy state signal complicated differentiation of bleedings from healthy state. A wearable microwave instrument has potential for accurate detection and monitoring of hemoperitoneum, with automated analysis making the instrument easy-to-use. Future hardware development is necessary to suppress measurement system variability and enable detection of smaller bleedings.

An amplitude-based characteristic parameter extraction algorithm for cerebral edema detection based on electromagnetic induction

Background

Cerebral edema is a common condition secondary to any type of neurological injury. The early diagnosis and monitoring of cerebral edema is of great importance to improve the prognosis. In this article, a flexible conformal electromagnetic two-coil sensor was employed as the electromagnetic induction sensor, associated with a vector network analyzer (VNA) for signal generation and receiving. Measurement of amplitude data over the frequency range of 1–100 MHz is conducted to evaluate the changes in cerebral edema. We proposed an Amplitude-based Characteristic Parameter Extraction (Ab-CPE) algorithm for multi-frequency characteristic analysis over the frequency range of 1–100 MHz and investigated its performance in electromagnetic induction-based cerebral edema detection and distinction of its acute/chronic phase. Fourteen rabbits were enrolled to establish cerebral edema model and the 24 h real-time monitoring experiments were carried out for algorithm verification.

Results

The proposed Ab-CPE algorithm was able to detect cerebral edema with a sensitivity of 94.1% and specificity of 95.4%. Also, in the early stage, it can detect cerebral edema with a sensitivity of 85.0% and specificity of 87.5%. Moreover, the Ab-CPE algorithm was able to distinguish between acute and chronic phase of cerebral edema with a sensitivity of 85.0% and specificity of 91.0%.

Conclusion

The proposed Ab-CPE algorithm is suitable for multi-frequency characteristic analysis. Combined with this algorithm, the electromagnetic induction method has an excellent performance on the detection and monitoring of cerebral edema.

Noninvasive and portable stroke type discrimination and progress monitoring based on a multichannel microwave transmitting-receiving system

The hemorrhagic and the ischemic types of stroke have similar symptoms in the early stage, but their treatments are completely different. The timely and effective discrimination of the two types of stroke can considerable improve the patients' prognosis. In this paper, a 16-channel and noncontact microwave-based stroke detection system was proposed and demonstrated for the potential differentiation of the hemorrhagic and the ischemic stroke. In animal experiments, 10 rabbits were divided into two groups. One group consisted of five cerebral hemorrhage models, and the other group consisted of five cerebral ischemia models. The two groups were monitored by the system to obtain the Euclidean distance transform value of microwave scattering parameters caused by pathological changes in the brain. The support vector machine was used to identify the type and the severity of the stroke. Based on the experiment, a discrimination accuracy of 96% between hemorrhage and ischemia stroke was achieved. Furthermore, the potential of monitoring the progress of intracerebral hemorrhage or ischemia was evaluated. The discrimination of different degrees of intracerebral hemorrhage achieved 86.7% accuracy, and the discrimination of different severities of ischemia achieved 94% accuracy. Compared with that with multiple channels, the discrimination accuracy of the stroke severity with a single channel was only 50% for the intracerebral hemorrhage and ischemia stroke. The study showed that the microwave-based stroke detection system can effectively distinguish between the cerebral hemorrhage and the cerebral ischemia models. This system is very promising for the prehospital identification of the stroke type due to its low cost, noninvasiveness, and ease of operation.

Multi-Frequency Electromagnetic Tomography for Acute Stroke Detection Using Frequency-Constrained Sparse Bayesian Learning

Imaging the bio-impedance distribution of the brain can provide initial diagnosis of acute stroke. This paper presents a compact and non-radiative tomographic modality, i.e. multi-frequency Electromagnetic Tomography (mfEMT), for the initial diagnosis of acute stroke. The mfEMT system consists of 12 channels of gradiometer coils with adjustable sensitivity and excitation frequency. To solve the image reconstruction problem of mfEMT, we propose an enhanced Frequency-Constrained Sparse Bayesian Learning (FC-SBL) to simultaneously reconstruct the conductivity distribution at all frequencies. Based on the Multiple Measurement Vector (MMV) model in the Sparse Bayesian Learning (SBL) framework, FC-SBL can recover the underlying distribution pattern of conductivity among multiple images by exploiting the frequency constraint information. A realistic 3D head model was established to simulate stroke detection scenarios, showing the capability of mfEMT to penetrate the highly resistive skull and improved image quality with FC-SBL. Both simulations and experiments showed that the proposed FC-SBL method is robust to noisy data for image reconstruction problems of mfEMT compared to the single measurement vector model, which is promising to detect acute strokes in the brain region with enhanced spatial resolution and in a baseline-free manner.

Development of a 3D Anthropomorphic Phantom Generator for Microwave Imaging Applications of the Head and Neck Region

The development of 3D anthropomorphic head and neck phantoms is of crucial and timely importance to explore novel imaging techniques, such as radar-based MicroWave Imaging (MWI), which have the potential to accurately diagnose Cervical Lymph Nodes (CLNs) in a neoadjuvant and non-invasive manner. We are motivated by a significant diagnostic blind-spot regarding mass screening of LNs in the case of head and neck cancer. The timely detection and selective removal of metastatic CLNs will prevent tumor cells from entering the lymphatic and blood systems and metastasizing to other body regions. The present paper describes the developed phantom generator which allows the anthropomorphic modelling of the main biological tissues of the cervical region, including CLNs, as well as their dielectric properties, for a frequency range from 1 to 10 GHz, based on Magnetic Resonance images. The resulting phantoms of varying complexity are well-suited to contribute to all stages of the development of a radar-based MWI device capable of detecting CLNs. Simpler models are essential since complexity could hinder the initial development stages of MWI devices. Besides, the diversity of anthropomorphic phantoms resulting from the developed phantom generator can be explored in other scientific contexts and may be useful to other medical imaging modalities.