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

Abstract

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.

Early assessment of acute ischemic stroke in rabbits based on multi-parameter near-field coupling sensing

“…The volume of CBF will decrease obviously after AIS. In addition, there is evidence that cerebral hemorrhage and AIS have different modes of influence on NFC signals [ 31 ]. Therefore, the early AIS detection method based on the development of near-field coupling technology meets the current clinical needs and has the theoretical feasibility.…”

Early Assessment of Acute Ischemic Stroke in Rabbits Based on Multi-Parameter Near-Field Coupling Sensing

“…The volume of CBF will decrease obviously after AIS. In addition, there is evidence that cerebral hemorrhage and AIS have different modes of in uence on NFC signals [28]. Therefore, the early AIS detection method based on the development of near-eld coupling technology meets the current clinical needs and has the theoretical feasibility.…”

Experimental Validation of the DBIM-TwIST Algorithm for Brain Stroke Detection and Differentiation Using a Multi-Layered Anatomically Complex Head Phantom

“…Machine learning approaches have also been proposed for brain stroke classification and they have shown to be potentially fast, robust, and accurate [22], [33]- [36]. More specifically, [37] conducted animal experiments using a non-contact microwave-based stroke detection system for classifying the type of the stroke, as well as monitoring the severity and the progress of the stroke by using different metrics. The main disadvantage of the abovementioned approaches is the lack of images which could limit their clinical adoption.…”