Your browser doesn't support javascript.
Deep-chest: Multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer chest diseases.
Ibrahim, Dina M; Elshennawy, Nada M; Sarhan, Amany M.
  • Ibrahim DM; Department of Computers and Control Engineering, Faculty of Engineering, Tanta University, Tanta, 31733, Egypt; Department of Information Technology, College of Computer, Qassim University, Buraydah, 51452, Saudi Arabia. Electronic address: d.hussein@qu.edu.sa.
  • Elshennawy NM; Department of Computers and Control Engineering, Faculty of Engineering, Tanta University, Tanta, 31733, Egypt. Electronic address: Nada_elshennawy@f-eng.tanta.edu.eg.
  • Sarhan AM; Department of Computers and Control Engineering, Faculty of Engineering, Tanta University, Tanta, 31733, Egypt. Electronic address: amany_sarhan@f-eng.tanta.edu.eg.
Comput Biol Med ; 132: 104348, 2021 05.
Article in English | MEDLINE | ID: covidwho-1141688
ABSTRACT
Corona Virus Disease (COVID-19) has been announced as a pandemic and is spreading rapidly throughout the world. Early detection of COVID-19 may protect many infected people. Unfortunately, COVID-19 can be mistakenly diagnosed as pneumonia or lung cancer, which with fast spread in the chest cells, can lead to patient death. The most commonly used diagnosis methods for these three diseases are chest X-ray and computed tomography (CT) images. In this paper, a multi-classification deep learning model for diagnosing COVID-19, pneumonia, and lung cancer from a combination of chest x-ray and CT images is proposed. This combination has been used because chest X-ray is less powerful in the early stages of the disease, while a CT scan of the chest is useful even before symptoms appear, and CT can precisely detect the abnormal features that are identified in images. In addition, using these two types of images will increase the dataset size, which will increase the classification accuracy. To the best of our knowledge, no other deep learning model choosing between these diseases is found in the literature. In the present work, the performance of four architectures are considered, namely VGG19-CNN, ResNet152V2, ResNet152V2 + Gated Recurrent Unit (GRU), and ResNet152V2 + Bidirectional GRU (Bi-GRU). A comprehensive evaluation of different deep learning architectures is provided using public digital chest x-ray and CT datasets with four classes (i.e., Normal, COVID-19, Pneumonia, and Lung cancer). From the results of the experiments, it was found that the VGG19 +CNN model outperforms the three other proposed models. The VGG19+CNN model achieved 98.05% accuracy (ACC), 98.05% recall, 98.43% precision, 99.5% specificity (SPC), 99.3% negative predictive value (NPV), 98.24% F1 score, 97.7% Matthew's correlation coefficient (MCC), and 99.66% area under the curve (AUC) based on X-ray and CT images.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: Pneumonia / Deep Learning / COVID-19 / Lung Neoplasms Type of study: Diagnostic study / Experimental Studies / Prognostic study Limits: Humans Language: English Journal: Comput Biol Med Year: 2021 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Pneumonia / Deep Learning / COVID-19 / Lung Neoplasms Type of study: Diagnostic study / Experimental Studies / Prognostic study Limits: Humans Language: English Journal: Comput Biol Med Year: 2021 Document Type: Article