Classification Framework for COVID-19 Diagnosis Based on Deep CNN Models

El-Shafai, W.; Algarni, Abeer D.; Banby, Ghada M. El; El‐Samie, Fathi E. Abd; Soliman, Naglaa F.

doi:10.32604/iasc.2022.020386

Cited by 10 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several CNN models with binary along with multi-class categorization of COVID-19 instances were studied by [ 29 ]. These models were tested on various CT alongside X-ray datasets using Transfer learning ideas for deep-tuning while fine-tuning settings.…”

Section: Related Workmentioning

confidence: 99%

Multi-modal medical image classification using deep residual network and genetic algorithm

et al. 2023

View full text Add to dashboard Cite

Artificial intelligence (AI) development across the health sector has recently been the most crucial. Early medical information, identification, diagnosis, classification, then analysis, along with viable remedies, are always beneficial developments. Precise and consistent image classification has critical in diagnosing and tactical decisions for healthcare. The core issue with image classification has become the semantic gap. Conventional machine learning algorithms for classification rely mainly on low-level but rather high-level characteristics, employ some handmade features to close the gap, but force intense feature extraction as well as classification approaches. Deep learning is a powerful tool with considerable advances in recent years, with deep convolution neural networks (CNNs) succeeding in image classification. The main goal is to bridge the semantic gap and enhance the classification performance of multi-modal medical images based on the deep learning-based model ResNet50. The data set included 28378 multi-modal medical images to train and validate the model. Overall accuracy, precision, recall, and F1-score evaluation parameters have been calculated. The proposed model classifies medical images more accurately than other state-of-the-art methods. The intended research experiment attained an accuracy level of 98.61%. The suggested study directly benefits the health service.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-modal medical image classification using deep residual network and genetic algorithm

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This does not produce explicit density but generates realistic images that can model samples of the correct distribution. In the first method, pixel value estimation is based on autoregression, such as PixelCNN [13] utilizing traceable density or the autoencoder method [14] applying approximate density. Likewise, GAN is based on implicit density and is considered a new way to generate various data from images, audio, and video [15].…”

Section: Super-resolution (Sr) Gan Phasementioning

confidence: 99%

Hybrid Single Image Super-Resolution Algorithm for Medical Images

El‐Shafai¹,

Mohamed²,

Zeghid³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

High-quality medical microscopic images used for diseases detection are expensive and difficult to store. Therefore, low-resolution images are favorable due to their low storage space and ease of sharing, where the images can be enlarged when needed using Super-Resolution (SR) techniques. However, it is important to maintain the shape and size of the medical images while enlarging them. One of the problems facing SR is that the performance of medical image diagnosis is very poor due to the deterioration of the reconstructed image resolution. Consequently, this paper suggests a multi-SR and classification framework based on Generative Adversarial Network (GAN) to generate high-resolution images with higher quality and finer details to reduce blurring. The proposed framework comprises five GAN models: Enhanced SR Generative Adversarial Networks (ESRGAN), Enhanced deep SR GAN (EDSRGAN), Sub-Pixel-GAN, SRGAN, and Efficient Wider Activation-B GAN (WDSR-b-GAN). To train the proposed models, we have employed images from the famous BreakHis dataset and enlarged them by 4× and 16× upscale factors with the ground truth of the size of 256 × 256 × 3. Moreover, several evaluation metrics like Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Structural Similarity Index (SSIM), Multiscale Structural Similarity Index (MS-SSIM), and histogram are applied to make comprehensive and objective comparisons to determine the best methods in terms of efficiency, training time, and storage space. The obtained results reveal the superiority of the proposed models over traditional and benchmark models in terms of color and texture restoration and detection by achieving an accuracy of 99.7433%.

show abstract

“…Menurut penelitian, lonjakan kasus ini disebabkan oleh pengenalan jenis virus corona baru dengan potensi infeksi yang sangat tinggi. Karakteritik ini membuat virus lebih menular daripada jenis virus corona yang ditemukan sebelumnya (El-Shafai et al, 2022;Gary et al, 2022).…”

Section: Sekilas Tentang Coronavirus Disease 2019unclassified

Diagnostik Klinis Infeksi SARS-CoV-2 dengan Metode Apusan

Sudaryati

Handayani

Sudiartawan

2022

INSOLOGI: Jurnal Sains dan Teknologi

View full text Add to dashboard Cite

COVID-19 has become a pandemic and has caused concern for people worldwide. The rapid spread of the disease requires health care providers and health workers to be able to diagnose precisely, quickly, and accurately to speed up the stages of treatment. Reviews and procedures for implementing clinical diagnostics of SARS-CoV-2 have not been widely reported. This study aimed to analyze the differences in diagnostic procedures for COVID-19 virus infection using the smear method at the Graha Medika Clinic. Observational descriptive research was conducted in July 2022. The research took place at the Graha Medika Clinic by screening patients who took the COVID-19 examination using the smear method (antigen swab, PCR swab, and rapid antigen). The study results obtained that one (10%) out of ten people infected with COVID-19 were on the antigen swab examination. There are differences in clinical diagnostics of COVID-19 infection using the smear method, namely in the antigen swab, the test time tends to be fast compared to PCR but is somewhat less accurate; rapid antigen only detects viruses that have taken place acutely with low accuracy while PCR is used as an accurate diagnostic by identifying proteins and viral glycans molecularly, has excellent accuracy but requires experts and a long time. The clinical diagnosis of COVID-19 infection using the smear method is currently adequate. The recommended examination method for the COVID-19 examination is carried out in stages, starting from rapid antigen, antigen swab, and PCR swab. PCR swab examination is the gold standard for detecting viral genetic material.

show abstract

Classification Framework for COVID-19 Diagnosis Based on Deep CNN Models

Cited by 10 publications

References 25 publications

Multi-modal medical image classification using deep residual network and genetic algorithm

Multi-modal medical image classification using deep residual network and genetic algorithm

Hybrid Single Image Super-Resolution Algorithm for Medical Images

Diagnostik Klinis Infeksi SARS-CoV-2 dengan Metode Apusan

Contact Info

Product

Resources

About