Comparison Analysis of CXR Images in Detecting Pneumonia Using VGG16 and ResNet50 Convolution Neural Network Model

Abstract

Pneumonia is a lung disease that causes serious fatalities worldwide. Pneumonia can be complicated for medical professionals to identify since it shares similarities with other lung diseases like lung cancer and cardiomegaly. Hospitals face difficulty finding professional radiologists who help to detect pneumonia through radioactive processes. This research proposes VGG16 and ResNet50-based system architecture using the Convolutional Neural Network (CNN) module, which allows the detection of pneumonia. This research identifies pneumonia using chest X-ray (CXR) images through VGG16 and ResNet50 of CNN model architectures. The performance of the proposed models is compared by performance parameters such as processing time, accuracy, and loss. The Pneumonia dataset was obtained from Kaggle and divided into 70% for training, 15 % for validation, and 15% for testing. The results show that the proposed ResNet50 model architecture has a better result than the VGG16 model architecture. It can be clearly observed based on both models' loss and accuracy results. Moreover, the processing time for ResNet50 in training and predicting the CXR images is much faster than the VGG16 model's processing time. Hence, ResNet50 performs better than VGG16 based on the result of loss and accuracy and the processing time for the model to train and predict the data. In conclusion, the findings show the capability of CNN models for detecting pneumonia in CXR images, thus reducing the burden of professional radiologists.

CSINet: Channel–Spatial Fusion Networks for Asymmetric Facial Expression Recognition

“…To verify the performance of facial expression recognition of the CSINet model proposed in this paper, ResNet50 [43] is selected as the baseline model (the backbone featureextraction network of the model in this paper is improved based on ResNet50) and representative spatially localized feature expression recognition networks (RAN, CVT) are used, as well as the expression recognition network that fuses the channel-spatial information (MA-Net, AMP-Net, VTFF, PACVT) for comparison. The network models in this paper follow the model training settings in Tables 1 and 2 and record the expression recognition accuracies obtained by different network models on different data sets.…”