A Novel Classification Model Using Optimal Long Short-Term Memory for Classification of COVID-19 from CT Images

Abstract

The human respiratory system is affected when an individual is infected with COVID-19, which became a global pandemic in 2020 and affected millions of people worldwide. However, accurate diagnosis of COVID-19 can be challenging due to small variations in typical and COVID-19 pneumonia, as well as the complexities involved in classifying infection regions. Currently, various deep learning (DL)-based methods are being introduced for the automatic detection of COVID-19 using computerized tomography (CT) scan images. In this paper, we propose the pelican optimization algorithm-based long short-term memory (POA-LSTM) method for classifying coronavirus using CT scan images. The data preprocessing technique is used to convert raw image data into a suitable format for subsequent steps. Here, we develop a general framework called no new U-Net (nnU-Net) for region of interest (ROI) segmentation in medical images. We apply a set of heuristic guidelines derived from the domain to systematically optimize the ROI segmentation task, which represents the dataset's key properties. Furthermore, high-resolution net (HRNet) is a standard neural network design developed for feature extraction. HRNet chooses the top-down strategy over the bottom-up method after considering the two options. It first detects the subject, generates a bounding box around the object and then estimates the relevant feature. The POA is used to minimize the subjective influence of manually selected parameters and enhance the LSTM's parameters. Thus, the POA-LSTM is used for the classification process, achieving higher performance for each performance metric such as accuracy, sensitivity, F1-score, precision, and specificity of 99%, 98.67%, 98.88%, 98.72%, and 98.43%, respectively.

Keywords: Computerized tomography scan images; Coronavirus; Disease prediction; High-resolution net; No new U-Net; Pelican optimization algorithm.

Fig. 1

Overview of POA-LSTM method

Fig. 2

An overview of the HRNet architecture

Fig. 3

Flowchart for the proposed method to classify COVID-19

Fig. 4

Accuracy analysis

Fig. 5

Precision analysis

Fig. 6

Sensitivity analysis of the POA-LSTM method

Fig. 7

Specificity analysis of the POA-LSTM method

Fig. 8

F1-score analysis

Fig. 9

ROC of the POA-LSTM method

Fig. 10

Confusion metrics of CT scan for COVID-19 classification dataset

Fig. 11

Confusion metrics of the SARS-Cov-2 dataset

Fig. 12

Confusion matrix for four categories using CT scan dataset

Fig. 13

Confusion matrix of four cases by the SARS-COV-2 dataset

Fig. 14

Segmentation results for COVID-19