Classification and detection of COVID-19 X-ray images based on fusion of DenseNet and VGG16 functionality


This article was originally published here

Biomedical signal process control. 2022 Aug;77:103772. doi: 10.1016/j.bspc.2022.103772. Published online May 8, 2022.

ABSTRACT

Since December 2019, the novel coronavirus disease (COVID-19) caused by the coronavirus syndrome strain 2 (SARS-CoV-2) has spread widely around the world and has become a serious global public health problem. For this high-velocity infectious disease, the application of X-rays to chest diagnosis plays a key role. In this study, we propose a method for classifying chest X-ray images based on the fusion of features from a dense convolutional network (DenseNet) and a visual geometry group network (VGG16). This paper adds an attention mechanism (global attention machine block and category attention block) to the model to extract deep features. A residual network (ResNet) is used to segment the effective image information to quickly obtain an accurate classification. The average accuracy of our model in detecting binary classification can reach 98.0%. The average accuracy for classification into three categories can reach 97.3%. The experimental results show that the proposed model performs well in this work. Therefore, the use of deep learning and feature fusion technology in the classification of chest radiographic images can become an auxiliary tool for clinicians and radiologists.

PMID:35573817 | CPM:PMC9080057 | DO I:10.1016/j.bspc.2022.103772

Previous League Of Their Own Reboot Images Gives First Look At Rockford Peaches
Next A Weakly Supervised Machine Learning Model for Extracting Features from Microscopy Images