Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms

Abstract

Highlights Radiographic chest images can be used to more accurately detect COVID-19 and assess disease severity. Among different imaging modalities, chest X-ray radiography has advantages of low cost, low radiation dose, wide accessibility and easy-to-operate in general or community hospitals. This study aims to develop and test a new deep learning model of chest X-ray images to detect COVID-19 induced pneumonia. For this purpose, we assembled a relatively large chest X-ray image dataset involving 8,474 cases, which are divided into three groups of COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) cases. After applying a preprocessing algorithm to detect and remove diaphragm regions depicting on images, a histogram equalization algorithm and a bilateral filter are applied to process the original images to generate two sets of filtered images. Then, the original image plus these two filtered images are used as inputs of three channels of the CNN deep learning model, which increase learning information of the model. In order to fully take advantages of the pre-optimized CNN models, this study uses a transfer learning method to build a new model to detect and classify COVID-19 infected pneumonia. A VGG16 based CNN model was originally trained using ImageNet and fine-tuned using chest X-ray images in this study. To reduce the bias in training and testing the CNN model, dataset is randomly divided into 3 subsets namely, training, validation, and testing with respect to the same frequency of cases in each class in all three COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) groups. Testing on a subset of 2544 cases, the CNN model yields 94.5% accuracy in classifying three subsets of cases and 98.1% accuracy in detecting COVID-19 infected pneumonia cases, which are significantly higher than the model directly trained using the original images without applying two image preprocessing steps to remove diaphragm and generate two filtered images.

Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans

“…Most of these papers used off-the-shelf networks, including ResNet-18 or ResNet-50 16,17,20,26,29,32,37 , DenseNet-121 27,28,31,32,34 , VGG-16 or VGG-19 19,33,35 , Inception 21,38 and EfficientNet 30,39 , with three considering custom architectures 18,25,36 and three using hand-engineered features [22][23][24] . Most papers classified images into the three classes, that is, COVID-19, non-COVID-19 pneumonia and normal 16,19,21,23,25,26,28,30,[32][33][34][35][36][37] , while two considered an extra class by dividing non-COVID-19 pneumonia into viral and bacterial pneumonia 17,29 . ResNet and DenseNet architectures showed better performance than the others, with accuracies ranging from 0.88 to 0.99.…”

“…We see that 20/32 papers have a reasonable balance between classes (with exceptions being refs. 17,24,26,30,31,33,36,37,40,51,61,62 . However, the majority of datasets were quite small, with 19/32 papers using fewer than 2,000 datapoints for development (with exceptions being refs.…”

“…However, the majority of datasets were quite small, with 19/32 papers using fewer than 2,000 datapoints for development (with exceptions being refs. 17,18,26,27,30,31,33,36,41,48,53,57,81 ). Only seven papers used both a dataset with more than 2,000 datapoints that was balanced for COVID-19 positive and the other classes 27,41,48,53,54,57,81 .…”

XCOVNet: Chest X-ray Image Classification for COVID-19 Early Detection Using Convolutional Neural Networks

“…As the infection of this virus mainly attacks the patients’ respiratory system [ 19 ], researchers mainly focused on detecting the disease level by finding the infection level using chest X-ray images [ 20 ], chest CT scan images [ 21 ] or cough sound recognition [ 22 ]. Researchers implemented various deep learning and computer vision methods to classify the patients of this infectious disease from healthy patients [ 15 , 23 , 24 ]. Accordingly, numerous deep learning models in the late literature aim to distinguish and order COVID-19 cases.…”

“…Abiyev and Ma’aitah [ 35 ] classified the chest X-rays images using CNN for the diagnosis of chest diseases. Heidari et al [ 23 ] demonstrated radio-graphic chest images to detect COVID-19 and assess disease severity. They collected around 8474 chest X-ray dataset images and divided in three groups: non-pneumonia, COVID-19 infected pneumonia and other community-acquired non-COVID-19 infected pneumonia cases.…”