EDNC: Ensemble Deep Neural Network for COVID-19 Recognition

Abstract

The automatic recognition of COVID-19 diseases is critical in the present pandemic since it relieves healthcare staff of the burden of screening for infection with COVID-19. Previous studies have proven that deep learning algorithms can be utilized to aid in the diagnosis of patients with potential COVID-19 infection. However, the accuracy of current COVID-19 recognition models is relatively low. Motivated by this fact, we propose three deep learning architectures, F-EDNC, FC-EDNC, and O-EDNC, to quickly and accurately detect COVID-19 infections from chest computed tomography (CT) images. Sixteen deep learning neural networks have been modified and trained to recognize COVID-19 patients using transfer learning and 2458 CT chest images. The proposed EDNC has then been developed using three of sixteen modified pre-trained models to improve the performance of COVID-19 recognition. The results suggested that the F-EDNC method significantly enhanced the recognition of COVID-19 infections with 97.75% accuracy, followed by FC-EDNC and O-EDNC (97.55% and 96.12%, respectively), which is superior to most of the current COVID-19 recognition models. Furthermore, a localhost web application has been built that enables users to easily upload their chest CT scans and obtain their COVID-19 results automatically. This accurate, fast, and automatic COVID-19 recognition system will relieve the stress of medical professionals for screening COVID-19 infections.

Keywords: COVID-19; CT scans; automatic recognition; deep learning; ensemble; transfer learning.

Figure 1

Flowchart of COVID-19 recognition system design.

Figure 2

CT scans of COVID-19 and non-COVID-19 patients. (a) CT scan of a COVID-19 patient. (b) CT scan of a non-COVID-19 (not normal) patient.

Figure 3

CT scans of COVID-19 and non-COVID-19 patients. (a) CT scan of a COVID-19 patient. (b) CT scan of a non-COVID-19 (not normal) patient.

Figure 4

Average pooling procedure.

Figure 5

The architecture of the modified pre-trained model.

Figure 6

The architecture of the F-EDNC model.

Figure 7

The architecture of the FC-EDNC model.

Figure 8

The architecture of the O-EDNC model.

Figure 9

The architecture of the CANet model.

Figure 10

The architecture of the COVID-19 recognition system.

Figure 11

A representation of the confusion matrix.

Figure 12

Confusion matrix result of the main dataset for sixteen modified pre-trained models in one hold-out run.

Figure 13

Learning curves of the main dataset for sixteen modified pre-trained models in one hold-out run.

Figure 14

Confusion matrix result for EDNC and CANet models in one hold-out run.

Figure 15

Learning curves for EDNC and CANet models in one hold-out run.

Figure 16

Overview of the frontend of the localhost web application.