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
. 2021 Oct;84(10):2254-2267.
doi: 10.1002/jemt.23779. Epub 2021 May 8.

An intelligence design for detection and classification of COVID19 using fusion of classical and convolutional neural network and improved microscopic features selection approach

Javaria Amin  1 , Muhammad Almas Anjum  2 , Muhammad Sharif  3 , Tanzila Saba  4 , Usman Tariq  5
Affiliations

An intelligence design for detection and classification of COVID19 using fusion of classical and convolutional neural network and improved microscopic features selection approach

Javaria Amin et al. Microsc Res Tech. 2021 Oct.

Abstract

Coronavirus19 is caused due to infection in the respiratory system. It is the type of RNA virus that might infect animal and human species. In the severe stage, it causes pneumonia in human beings. In this research, hand-crafted and deep microscopic features are used to classify lung infection. The proposed work consists of two phases; in phase I, infected lung region is segmented using proposed U-Net deep learning model. The hand-crafted features are extracted such as histogram orientation gradient (HOG), noise to the harmonic ratio (NHr), and segmentation based fractal texture analysis (SFTA) from the segmented image, and optimum features are selected from each feature vector using entropy. In phase II, local binary patterns (LBPs), speeded up robust feature (Surf), and deep learning features are extracted using a pretrained network such as inceptionv3, ResNet101 from the input CT images, and select optimum features based on entropy. Finally, the optimum selected features using entropy are fused in two ways, (i) The hand-crafted features (HOG, NHr, SFTA, LBP, SURF) are horizontally concatenated/fused (ii) The hand-crafted features (HOG, NHr, SFTA, LBP, SURF) are combined/fused with deep features. The fused optimum features vector is passed to the ensemble models (Boosted tree, bagged tree, and RUSBoosted tree) in two ways for the COVID19 classification, (i) classification using fused hand-crafted features (ii) classification using fusion of hand-crafted features and deep features. The proposed methodology is tested /evaluated on three benchmark datasets. Two datasets employed for experiments and results show that hand-crafted & deep microscopic feature's fusion provide better results compared to only hand-crafted fused features.

Keywords: U-Net; ensemble methods; entropy; fusion; hand crafted features; healthcare; public health.

PubMed Disclaimer

Conflict of interest statement

All authors declared that there is no conflict of interest.

Figures

FIGURE 1
FIGURE 1
Proposed model for segmentation and classification of healthy/COVID‐19 images
FIGURE 2
FIGURE 2
U‐Net model for COVID‐19 segmentation
FIGURE 3
FIGURE 3
Segmentation results with ground truth (a) input images (b) segmentation by proposed method (c) manually ground truth images
FIGURE 4
FIGURE 4
Noise to the harmonic ratio (NHr) features (a) input image (b) NHr
FIGURE 5
FIGURE 5
SURF features (a) original image (b) SURF features
FIGURE 6
FIGURE 6
Histogram orientation gradient (HOG) features (a) original image (b) HOG
FIGURE 7
FIGURE 7
Local binary patterns (LBP) of the original image
FIGURE 8
FIGURE 8
SFTA features
FIGURE 9
FIGURE 9
DCNN features
FIGURE 10
FIGURE 10
Features extraction, selection, and fusion process for COVID‐19 classification
FIGURE 11
FIGURE 11
Segmentation outcome on COVID‐19 segmentation dataset
FIGURE 12
FIGURE 12
Segmentation outcome on POF Hospital dataset
FIGURE 13
FIGURE 13
Ensemble prediction model based on hand crafted features vector
FIGURE 14
FIGURE 14
Confusion matrix using ensemble methods (a) bagged tree, (b) RUSBoosted tree, (c) Boosted tree
FIGURE 15
FIGURE 15
An ensemble prediction model based on hand‐crafted and deep features fusion
FIGURE 16
FIGURE 16
AUC across ROC of ensemble methods (a) Bagged tree, (b) Boosted tree, (c) RUSBoosted tree
See this image and copyright information in PMC

References

    1. Acharya, U. R. , Fernandes, S. L. , WeiKoh, J. E. , Ciaccio, E. J. , Fabell, M. K. M. , Tanik, U. J. , … Yeong, C. H. (2019). Automated detection of Alzheimer's disease using brain MRI images–a study with various feature extraction techniques. Journal of Medical Systems, 43(9), 302. - PubMed
    1. Albahri, O. , Zaidan, A. , Albahri, A. , Zaidan, B. , Abdulkareem, K. H. , Al‐Qaysi, Z. , … Rashid, N. A. (2020a). Systematic review of artificial intelligence techniques in the detection and classification of COVID‐19 medical images in terms of evaluation and benchmarking: Taxonomy analysis, challenges, future solutions and methodological aspects. Journal of Infection and Public Health, 13(10), 1381–1396. - PMC - PubMed
    1. Albahri, O. , Zaidan, A. , Albahri, A. , Zaidan, B. , Abdulkareem, K. H. , Al‐Qaysi, Z. , … Health, P. (2020b). Systematic review of artificial intelligence techniques in the detection and classification of COVID‐19 medical images in terms of evaluation and benchmarking: Taxonomy analysis, challenges, future solutions and methodological aspects, 13(10), 1381–1396. - PMC - PubMed
    1. Bay, H. , Ess, A. , Tuytelaars, T. , & Van Gool, L. (2008). Speeded‐up robust features (SURF). Computer Vision and Image Understanding, 110(3), 346–359.
    1. Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.

LinkOut - more resources