Architecture-based Evaluation of VGG16 and ResNet Models for an Online Deep Learning Environment for Medical Applications

Image classification using deep learning models has evolved impressively well in the past decade. Datasets containing millions of images grouped into thousands of classes have been used to train and test these models. Medical image classification however still faces the challenge of scarcity in datasets. Gathering data from various locations and placing it in a commonly accessed dataset is highly time-consuming. Diseases need real-Time response just like any other mission-critical operation and online deep learning could be handy. There are many pre-Trained models which acquired good accuracy on large datasets. But as the depth of the model increases the time taken to train the model and the number of computations also increase. In this paper, we evaluated two models with different architectures. VGG16 is a 16-layer normal stack of convolutional layers and ResNet50V2 is a stack of residual blocks with skip connections and 50 layers. We used a Computer Tomography (CT) Lung image dataset to classify images into COVID, healthy and pneumonia images. We found that VGG16 is taking lesser time and computations with reduced loss when compared to the ResNet50V2 model. We finally conclude that ResNet50V2 is taking more time to train images as the model is 50 layers deep, whereas the VGG16 model is only 16 layers deep. Also, images that show mild infection were predicted as healthy images by ResNet50V2 but predicted correctly by the VGG16 model. © 2022 IEEE.

Parameter based Performance Evaluation of Deep Learning Models for Classification of CoViD and Pneumonia CT Images

Computer Tomography (CT) scan is one of the widely used techniques to identify Corona Virus Disease-2019. The presence of infection is identified using ground glass opacity in these images. Sometimes, there are very few changes that cannot be identified with the naked eye. Deep learning algorithms can be used to classify such images. Many deep learning algorithms have performed exceptionally well in classifying images. In this paper, we evaluated VGG16 and Xception models and found that the Xception model has a large number of non-trainable parameters. VGG16 model uses a normal convolution and Xception uses a depth wise separable convolution with Batch Normalization. Our results show that VGG16 performs better in classifying CoViD CT Images than the Xception model. We conclude that due to the Batch Normalization Xception model has non-trainable parameters and shows low performance when lesser images are used to train the model. However, VGG16 was found to perform very well even on images with subtle opacity. © 2021 IEEE.