Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Oct;60(10):2931-2949.
doi: 10.1007/s11517-022-02637-6. Epub 2022 Aug 12.

COVID-19 diagnosis using chest CT scans and deep convolutional neural networks evolved by IP-based sine-cosine algorithm

Binfeng Xu  1 , Diego Martín  2 , Mohammad Khishe  3 , Reza Boostani  4
Affiliations

COVID-19 diagnosis using chest CT scans and deep convolutional neural networks evolved by IP-based sine-cosine algorithm

Binfeng Xu et al. Med Biol Eng Comput. 2022 Oct.

Abstract

The prevalence of the COVID-19 virus and its variants has influenced all aspects of our life, and therefore, the precise diagnosis of this disease is vital. If a polymerase chain reaction test for a subject is negative, but he/she cannot easily breathe, taking a computed tomography (CT) image from his/her lung is urgently recommended. This study aims to optimize a deep convolution neural network (DCNN) structure to increase the COVID-19 diagnosis accuracy in lung CT images. This paper employs the sine-cosine algorithm (SCA) to optimize the structure of DCNN to take raw CT images and determine their status. Three improvements based on regular SCA are proposed to enhance both the accuracy and speed of the results. First, a new encoding approach is proposed based on the internet protocol (IP) address. Then, an enfeebled layer is proposed to generate a variable-length DCNN. The suggested model is examined over the COVID-CT and SARS-CoV-2 datasets. The proposed method is compared to a standard DCNN and seven variable-length models in terms of five known metrics, including sensitivity, accuracy, specificity, F1-score, precision, and receiver operative curve (ROC) and precision-recall curves. The results demonstrate that the proposed DCNN-IPSCA surpasses other benchmarks, achieving final accuracy of (98.32% and 98.01%), the sensitivity of (97.22% and 96.23%), and specificity of (96.77% and 96.44%) on the SARS-CoV-2 and COVID-CT datasets, respectively. Also, the proposed DCNN-IPSCA performs much better than the standard DCNN, with GPU and CPU training times, which are 387.69 and 63.10 times faster, respectively.

Keywords: COVID-19; Chest CT scans; DCNNs; Internet protocol address; Sine-cosine algorithm.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
The LeNet-5 architecture
Fig. 2
Fig. 2
Range reduction of the sine and cosine values during iterations
Fig. 3
Fig. 3
Typical CT images from the SARS-CoV-2 CT-scan dataset
Fig. 4
Fig. 4
The representation of two images with different sizes and contrast
Fig. 5
Fig. 5
An illustration of the standard image (left image) and its enhanced version (right image)
Algorithm 1
Algorithm 1
Framework of IPSCA
Fig. 6
Fig. 6
An IP address from a candid solution with five DCNN layers
Fig. 7
Fig. 7
The illustration of an encoded candid solution vector
Algorithm 2
Algorithm 2
The evaluation of fitness function
Fig. 8
Fig. 8
The EPG for the SARS-CoV-2 CT-Scan dataset
Fig. 9
Fig. 9
The EPG for the COVID-CT dataset
Fig. 10
Fig. 10
The confusion matrix for the SARS-CoV-2 CT-Scan dataset
Fig. 11
Fig. 11
The confusion matrix for the COVID-CT dataset
Fig. 12
Fig. 12
The precision-recall and ROC curves for the SARS-CoV-2 dataset
Fig. 13
Fig. 13
The precision-recall and ROC curves for the COVID-CT dataset
Fig. 14
Fig. 14
The convergence curves for utilized benchmark algorithms
Fig. 15
Fig. 15
The results of the control parameters
Fig. 16
Fig. 16
Typical example of the feature map for input images: a COVID19 and b non-COVID19
Fig. 17
Fig. 17
Typical example of masked images for a COVID19 and b Non-COVID19 input
Fig. 18
Fig. 18
The CAM demonstration results for the two typical COVID19 examples
Fig. 19
Fig. 19
The CAM demonstration results for the two typical non-COVID19 examples
See this image and copyright information in PMC

References

    1. Panwar H, Gupta PK, Siddiqui MK, Morales-Menendez R, Singh V. Application of deep learning for fast detection of COVID-19 in X-Rays using nCOVnet, Chaos. Solitons and Fractals. 2020 doi: 10.1016/j.chaos.2020.109944. - DOI - PMC - PubMed
    1. Zhang J, Xie Y, Li Y, Shen C, Xia Y (2020) COVID-19 screening on chest X-ray images using deep learning based anomaly detection, aeXiv.2002.12338v1
    1. Han G, et al. Hybrid resampling and multi-feature fusion for automatic recognition of cavity imaging sign in lung CT. Futur. Gener. Comput. Syst. 2019;99:558–570. doi: 10.1016/j.future.2019.05.009. - DOI
    1. Lella KK, Pja A. Automatic diagnosis of COVID-19 disease using deep convolutional neural network with multi-feature channel from respiratory sound data: cough, voice, and breath. Alexandria Eng. J. 2022;61(2):1319–1334. doi: 10.1016/j.aej.2021.06.024. - DOI
    1. Khishe M, Caraffini F, Kuhn S. Evolving deep learning convolutional neural networks for early COVID-19 detection in chest X-ray images. Mathematics. 2021;9(9):1002. doi: 10.3390/math9091002. - DOI