COVID-19 detection from chest X-ray images using CLAHE-YCrCb, LBP, and machine learning algorithms

Abstract

Background: COVID-19 is a disease that caused a contagious respiratory ailment that killed and infected hundreds of millions. It is necessary to develop a computer-based tool that is fast, precise, and inexpensive to detect COVID-19 efficiently. Recent studies revealed that machine learning and deep learning models accurately detect COVID-19 using chest X-ray (CXR) images. However, they exhibit notable limitations, such as a large amount of data to train, larger feature vector sizes, enormous trainable parameters, expensive computational resources (GPUs), and longer run-time.

Results: In this study, we proposed a new approach to address some of the above-mentioned limitations. The proposed model involves the following steps: First, we use contrast limited adaptive histogram equalization (CLAHE) to enhance the contrast of CXR images. The resulting images are converted from CLAHE to YCrCb color space. We estimate reflectance from chrominance using the Illumination-Reflectance model. Finally, we use a normalized local binary patterns histogram generated from reflectance (Cr) and YCb as the classification feature vector. Decision tree, Naive Bayes, support vector machine, K-nearest neighbor, and logistic regression were used as the classification algorithms. The performance evaluation on the test set indicates that the proposed approach is superior, with accuracy rates of 99.01%, 100%, and 98.46% across three different datasets, respectively. Naive Bayes, a probabilistic machine learning algorithm, emerged as the most resilient.

Conclusion: Our proposed method uses fewer handcrafted features, affordable computational resources, and less runtime than existing state-of-the-art approaches. Emerging nations where radiologists are in short supply can adopt this prototype. We made both coding materials and datasets accessible to the general public for further improvement. Check the manuscript's availability of the data and materials under the declaration section for access.

Keywords: CLAHE; COVID-19; HE; LBP; Max–Min filter; YCrCb.

Fig. 1

Flowchart of the proposed model

Fig. 2

Rowwise First row: Normal images. Second row: COVID-19 images. Third row: pneumonia images. Columnwise First column: not enhanced images. Second column: images enhanced with HE. Third column: images enhanced with CLAHE

Fig. 3

The top first row corresponds to COVID-19, normal, and pneumonia chest X-Ray images. The second row corresponds to the LBP image transformation of COVID-19, normal, and pneumonia

Fig. 4

The first row depicts the CXR image with annotated abnormal regions (yellow circle). The second row highlights their corresponding rainbow transformations

Fig. 5

The first row depicts COVID-19 images. Whereas the second row shows normal images. These images were randomly selected from [16] dataset

Fig. 6

Data distribution (dataset A [16], dataset B [43], and dataset C [44])

Fig. 7

Receiver operating characteristic (ROC) curve

Fig. 8

Confusion matrix portraying the plotted ROC in Fig. 7 using [16] dataset

Fig. 9

Graphical plot of ROC curve

Fig. 10

Confusion matrix portraying the plotted ROC in Fig. 9 using [16] dataset

Fig. 11

Receiver operating characteristic (ROC) curve

Fig. 12

Confusion matrix portraying the plotted ROC in Fig. 11 using [43] dataset

Fig. 13

The receiver operating characteristic (ROC) curve

Fig. 14

Confusion matrix portraying the plotted ROC in Fig. 13 using [44] dataset

Fig. 15

Graphs a, b, c, and d correspond to section one, section two, and section 3 experiments, respectively

Fig. 16

Graphs A and B, C and D correspond to the confidence interval and PR curve of the performed experiments, section one and three respectively