A Deep Batch Normalized Convolution Approach for Improving COVID-19 Detection from Chest X-ray Images

Abstract

Pre-trained machine learning models have recently been widely used to detect COVID-19 automatically from X-ray images. Although these models can selectively retrain their layers for the desired task, the output remains biased due to the massive number of pre-trained weights and parameters. This paper proposes a novel batch normalized convolutional neural network (BNCNN) model to identify COVID-19 cases from chest X-ray images in binary and multi-class frameworks with a dual aim to extract salient features that improve model performance over pre-trained image analysis networks while reducing computational complexity. The BNCNN model has three phases: Data pre-processing to normalize and resize X-ray images, Feature extraction to generate feature maps, and Classification to predict labels based on the feature maps. Feature extraction uses four repetitions of a block comprising a convolution layer to learn suitable kernel weights for the features map, a batch normalization layer to solve the internal covariance shift of feature maps, and a max-pooling layer to find the highest-level patterns by increasing the convolution span. The classifier section uses two repetitions of a block comprising a dense layer to learn complex feature maps, a batch normalization layer to standardize internal feature maps, and a dropout layer to avoid overfitting while aiding the model generalization. Comparative analysis shows that when applied to an open-access dataset, the proposed BNCNN model performs better than four other comparative pre-trained models for three-way and two-way class datasets. Moreover, the BNCNN requires fewer parameters than the pre-trained models, suggesting better deployment suitability on low-resource devices.

Keywords: COVID-19; batch normalized convolutional neural network (BNCNN); chest X-ray; classification; deep learning.

Figure 1

Example of pre-processed X-ray images for (a) COVID-19, (b) Normal, and (c) Viral Pneumonia.

Figure 2

Proposed BNCNN model for COVID-19 detection.

Figure 3

Confusion matrices of the BNCNN model for (a) three-way and (b) two-way classification (red: FP, yellow: FN, green: TP, and blue: TN for COVID-19 class).

Figure 4

Variation of accuracy and loss of the BNCNN model on training and validation datasets over 100 epochs, (a) three-way and (b) two-way classification.

Figure 5

Average ranking based on testing accuracy at (the Friedman test) for (a) three-way (p = 0.0146) and (b) two-way (p = 0.0053) classification.

Figure 6

AUC and DeLong test for proposed BNCNN and other models for (a) three-way and (b) two-way classification.