Screening COVID-19 from Chest X-ray Images by Optical Diffractive Neural Network with the Optimized F number

• JiaLong Wang, Shouyu Chai, Wenting Gu, Boyi Li, Xue Jiang, Yunxiang Zhang, Hongen Liao, Xin liu, and Dean Ta
• received 11/20/2023; accepted 04/07/2024; posted 04/08/2024; Doc. ID 513537
• Abstract: The COVID-19 pandemic continues to significantly impact people’s lives worldwide, emphasizing the critical need for effective detection methods. Many existing deep learning-based approaches for COVID-19 detection offer high accuracy but demand substantial computing resources, time, and energy. In this study, we introduce an optical diffraction neural network (ODNN-COVID) that distinguish itself with low power consumption, efficient parallelization, and fast computing speed for COVID-19 detection. Our system achieves an impressive overall accuracy of 92.64% in binary-classification and 88.89% in three-classification diagnosis tasks. In addition, we explore how the physical parameters of ODNN-COVID affect its diagnostic performance. We identify the F number as a key parameter for evaluating the overall detection capabilities. Through an assessment of the connectivity of the diffraction network, we established an optimized range of F numbers, offering guidance for constructing optical diffraction neural networks. Both simulations and experiments validate that our proposed optical diffractive neural network serve as a passive optical processor for effective COVID-19 diagnosis, featuring low power consumption, high parallelization, and fast computing capabilities. Furthermore, ODNN-COVID exhibits versatility, making it adaptable to various image analysis and object classification tasks related to medical fields owing to its general architecture.