A pneumonia detection system based on MobileNetv2 network and model callback

Abstract

This study focuses on automatically classifying radiographic images of the chest region into standard classification, COVID-19 classification, and viral pneumonia classification by utilizing complex neural networks. Using a chest radiograph dataset from the academic bastion Université de Montréal, the study introduces an innovative paradigm rooted in MobileNetV2. We conducted a comparative analysis to evaluate the efficacy of this avant-garde model by juxtaposing it with the typical DenseNet121 and RESNET50 popular in the field of medical image classification. This exploration revealed MobileNetV2 as an ingenious model distinguished by its tiny scale and commendable accuracy. Using DW convolution design greatly reduces the computational complexity and parameter count. Regarding the composition of the architecture, transfer learning is used to attach global mean pooling and fully connected layers on top of MobileNetV2, and is customized for nuanced tripartite classification work. Comparative evaluation shows that the MobileNetV2 model has only 2,643,187 parameters, completes training in just 37 seconds, and has an accuracy of 98.48%. In contrast, although DenseNet121 and RESNET50 demonstrate commendable proficiency, their large model dimensions and lengthy training intervals limit their usefulness in resource-limited environments. The findings highlight the superior performance of the MobileNetV2 model in the field of chest X-ray classification, providing a simplified and efficient alternative for deployment on mobile and embedded devices.