Detection of Covid-19 in Chest X-ray Image using CLAHE and Convolutional Neural Network

Umri, Buyut Khoirul; Akhyari, Muhammad Wafa; Kusrini, Kusrini

doi:10.1109/icoris50180.2020.9320806

Cited by 48 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The visual quality of input medical images such as MRI and SPECT images are improved by applying contrast limited adaptive histogram equalization (CLAHE) technique [ 18 , 19 ]. Instead of operating on entire image pixels, CLAHE operates only on a small region of the image called tiles [ 20 , 21 ].…”

Section: Methodsmentioning

confidence: 99%

Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine

Nanmaran

Srimathi

Yamuna

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Image fusion can be performed on images either in spatial domain or frequency domain methods. Frequency domain methods will be most preferred because these methods can improve the quality of edges in an image. In image fusion, the resultant fused images will be more informative than individual input images, thus more suitable for classification problems. Artificial intelligence (AI) algorithms play a significant role in improving patient’s treatment in the health care industry and thus improving personalized medicine. This research work analyses the role of image fusion in an improved brain tumour classification model, and this novel fusion-based cancer classification model can be used for personalized medicine more effectively. Image fusion can improve the quality of resultant images and thus improve the result of classifiers. Instead of using individual input images, the high-quality fused images will provide better classification results. Initially, the contrast limited adaptive histogram equalization technique preprocess input images such as MRI and SPECT images. Benign and malignant class brain tumor images are applied with discrete cosine transform-based fusion method to obtain fused images. AI algorithms such as support vector machine classifier, KNN classifier, and decision tree classifiers are tested with features obtained from fused images and compared with the result obtained from individual input images. Performances of classifiers are measured using the parameters accuracy, precision, recall, specificity, and F 1 score. SVM classifier provided the maximum accuracy of 96.8%, precision of 95%, recall of 94%, specificity of 93%, F 1 score of 91%, and performed better than KNN and decision tree classifiers when extracted features from fused images are used. The proposed method results are compared with existing methods and provide satisfactory results.

show abstract

Section: Methodsmentioning

confidence: 99%

Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine

Nanmaran

Srimathi

Yamuna

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Li and Xia [2] reported GGO and consolidation, interlobular septal thickening and air bronchogram sign, with or without vascular expansion, as common CT features of COVID-19 patients. Peripheral focal or multifocal GGO affecting both lungs in 50%-75% of patients is another observation.…”

Section: Literature Riviewmentioning

confidence: 98%

An Effective Deep Learning Approach Based On CNN to Predict COVID-19 Rapidly Using Chest Images

Shing¹,

Rana²,

Basher³

et al. 2021

IJRIAS

View full text Add to dashboard Cite

In December 2019 the novel coronavirus which first appeared in Wuhan City of China spread rapidly around the world and became a pandemic. It has caused a devastating effect on daily lives, public health, and the global economy. As soon as possible we have to detect the affected patient and quickly treat them. There are no accurate automated toolkits available so the need for auxiliary diagnostic tools has increased. Modern outcomes attained using radiology imaging systems recommend that such images have salient evidence about the COVID-19 virus. Real-time reverse transcription-polymerase chain reaction (RT-PCR) is the most common test technique currently used for COVID-19 diagnosis that is too much time-consuming. Using artificial intelligence (AI) techniques associated with radiological imaging can be helpful for the accurate detection of this disease and can also be assistive to overcome the problem of an absence of specialized doctors in remote communities. In this paper, a new model based on Convolutional Neural Network (CNN) that automatically detects COVID-19 using chest images is presented. The proposed model is designed to provide accurate diagnostics for binary classification. A computer vision is rapidly relieved day by day. During our study, we observed that most of the affected people have no common symptoms before checkup COVID-19. If the detection results are incorrect, the patient will not be able to understand that he or she has Covid-19. The proposed model is evaluated by Python libraries namely TensorFlow and Keras. In the proposed model, we got 95% accuracy as well as the detection of COVID-19 is fast.

show abstract

“…Each enhancement method's output image will be analyzed using a Blind/Reference-less Image Spatial Quality Evaluator (BRISQUE). BRISQUE is a referenceless quality assessment technique [16,17]. To some extent, it is a comprehensive evaluation metric that makes use of 'natural scene statistics' to evaluate both the lack of 'naturalness' in an image and the presence of distortions.…”

Section: Blind/referenceless Image Spatial Quality Evaluator (Brisque)mentioning

confidence: 99%

Multi-temporal satellite image correction based on CNN features and adaptive contrast enhancement

Saberi

Hashim

Ali

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

In recent years, identifying changes in multi-temporal images in terms of land use and land cover has been significant in a variety of applications, including urban planning. Due to weather and environmental effects, optical remote sensing has limitations in obtaining images where the image quality may be degraded. It’s because the images being registered are taken at various times, viewpoints, and types of sensors. In this article, the pre-processing methods, which include radiometric correction and geometric correction, are introduced to enhance the quality of satellite images and identify correct spatial alignment. For radiometric correction, adaptive contrast enhancement is done by combining histogram- and non-linear transfer function-based approaches in CIELAB color space. A comparison study is done to see how the new method compared to other methods. For geometric correction, the features from two images are extracted using Convolutional Neural Network to match and align them. The introduced approach for radiometric correction gave the best average rank of BRISQUE scores and RMSE of contrast scores, and the geometric correction can align two images together with an average accuracy of improvement of 91.78 percent. The findings of this research will provide the preliminary step for any change detection activities.

show abstract

Detection of Covid-19 in Chest X-ray Image using CLAHE and Convolutional Neural Network

Cited by 48 publications

References 11 publications

Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine

Investigating the Role of Image Fusion in Brain Tumor Classification Models Based on Machine Learning Algorithm for Personalized Medicine

An Effective Deep Learning Approach Based On CNN to Predict COVID-19 Rapidly Using Chest Images

Multi-temporal satellite image correction based on CNN features and adaptive contrast enhancement

Contact Info

Product

Resources

About