Efficient Pneumonia Detection Method and Implementation in Chest X-ray Images Based on a Neuromorphic Spiking Neural Network

Abstract

Deep Learning has solved numerous problems in image recognition and information processing, and is currently being employed in tackling the coronavirus disease (COVID-19) which has become a pandemic. Incisively, deep learning models are utilized in diagnosis systems as a method to detect COVID-19 related pneumonia by analyzing lung X-ray images of patients. The accuracy of this method is in the range of 80–90%. However, it is computationally complex, requires high power, and has low energy efficiency. Consequently, it is not suitable a diagnosis/detection method to be deployed on the edge. In this paper, we propose an efficient pneumonia (COVID-19) detection method and implementation in chest x-ray images based on a neuromorphic spiking neural network. This method is implemented on our previously proposed AI-enabled real-time biomedical system AIRBiS (AIRBiS project: u-aizu.ac.jp/misc/benablab/airbis.html ) which is based on a high-performance low-power re-configurable AI-chip for inference, and an interactive user interface for effective operation and monitoring. The evaluation results show that the proposed method achieves 92.1%, and 80.7% detection accuracy of pneumonia (i.e., COVID-19) over-collected test data.