LDDNet: A Deep Learning Framework for the Diagnosis of Infectious Lung Diseases

Abstract

This paper proposes a new deep learning (DL) framework for the analysis of lung diseases, including COVID-19 and pneumonia, from chest CT scans and X-ray (CXR) images. This framework is termed optimized DenseNet201 for lung diseases (LDDNet). The proposed LDDNet was developed using additional layers of 2D global average pooling, dense and dropout layers, and batch normalization to the base DenseNet201 model. There are 1024 Relu-activated dense layers and 256 dense layers using the sigmoid activation method. The hyper-parameters of the model, including the learning rate, batch size, epochs, and dropout rate, were tuned for the model. Next, three datasets of lung diseases were formed from separate open-access sources. One was a CT scan dataset containing 1043 images. Two X-ray datasets comprising images of COVID-19-affected lungs, pneumonia-affected lungs, and healthy lungs exist, with one being an imbalanced dataset with 5935 images and the other being a balanced dataset with 5002 images. The performance of each model was analyzed using the Adam, Nadam, and SGD optimizers. The best results have been obtained for both the CT scan and CXR datasets using the Nadam optimizer. For the CT scan images, LDDNet showed a COVID-19-positive classification accuracy of 99.36%, a 100% precision recall of 98%, and an F1 score of 99%. For the X-ray dataset of 5935 images, LDDNet provides a 99.55% accuracy, 73% recall, 100% precision, and 85% F1 score using the Nadam optimizer in detecting COVID-19-affected patients. For the balanced X-ray dataset, LDDNet provides a 97.07% classification accuracy. For a given set of parameters, the performance results of LDDNet are better than the existing algorithms of ResNet152V2 and XceptionNet.

Keywords: COVID-19; CT scan; DenseNet201; ResNet152V2; X-ray; XceptionNet; infectious disease.

Figure 1

A sample of the experimental CT scan dataset: (a) normal or non-COVID-19, (b) COVID-19, and (c) community-acquired pneumonia (CAP).

Figure 2

A sample of the experimental chest X-ray dataset: (a) normal or healthy chest, (b) COVID-19, and (c) pneumonia.

Figure 3

Basic summary of our proposed work for CT scan images.

Figure 4

Basic summary of our proposed work for X-ray images.

Figure 5

LDDNet architecture [57].

Figure 6

Confusion matrix for CT images using LDDNet: (a) Adam optimizer, (b) Nadam optimizer, and (c) SGD optimizer.

Figure 6

Confusion matrix for CT images using LDDNet: (a) Adam optimizer, (b) Nadam optimizer, and (c) SGD optimizer.

Figure 7

(a) ROC curve for CT images using LDDNet with Adam optimizer, (b) ROC curve for CT images using LDDNet with Nadam optimizer, and (c) ROC curve for CT images using LDDNet with SGD optimizer.

Figure 8

Confusion matrix for LDDNet: (a) Adam optimizer, (b) Nadam optimizer, and (c) SGD optimizer.

Figure 8

Confusion matrix for LDDNet: (a) Adam optimizer, (b) Nadam optimizer, and (c) SGD optimizer.

Figure 9

ROC curve for LDDNet: (a) Adam optimizer, (b) Nadam optimizer, and (c) SGD optimizer.