Fast COVID-19 and Pneumonia Classification Using Chest X-ray Images

Luján-García, Juan Eduardo; Moreno-Ibarra, Marco; Villuendas-Rey, Yenny; Yáñez-Márquez, Cornelio

doi:10.3390/math8091423

Cited by 37 publications

(33 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, a huge number of CNN models exist and are used for distinct purposes. As a result, we can find custom models [ 16 , 19 , 31 ] and the ones that use key baselines for classification of different diseases [ 17 , 22 , 24 , 29 , 41 , 42 , 43 ].…”

Section: Methodsmentioning

confidence: 99%

“…Moreover, Yu et al [ 23 ] presented a framework that used four pretrained CNNs as baseline to classify among patients using CT scans, obtaining accuracies superior to 94%. Luján-García et al [ 24 ] used an Xception CNN to classify among COVID-19 and pneumonia patients using a pretrained model on ImageNet. They showed that the Xception network was the fastest among several baselines.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NanoChest-Net: A Simple Convolutional Network for Radiological Studies Classification

et al. 2021

Self Cite

View full text Add to dashboard Cite

The new coronavirus disease (COVID-19), pneumonia, tuberculosis, and breast cancer have one thing in common: these diseases can be diagnosed using radiological studies such as X-rays images. With radiological studies and technology, computer-aided diagnosis (CAD) results in a very useful technique to analyze and detect abnormalities using the images generated by X-ray machines. Some deep-learning techniques such as a convolutional neural network (CNN) can help physicians to obtain an effective pre-diagnosis. However, popular CNNs are enormous models and need a huge amount of data to obtain good results. In this paper, we introduce NanoChest-net, which is a small but effective CNN model that can be used to classify among different diseases using images from radiological studies. NanoChest-net proves to be effective in classifying among different diseases such as tuberculosis, pneumonia, and COVID-19. In two of the five datasets used in the experiments, NanoChest-net obtained the best results, while on the remaining datasets our model proved to be as good as baseline models from the state of the art such as the ResNet50, Xception, and DenseNet121. In addition, NanoChest-net is useful to classify radiological studies on the same level as state-of-the-art algorithms with the advantage that it does not require a large number of operations.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

NanoChest-Net: A Simple Convolutional Network for Radiological Studies Classification

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Even though the number of parameters is substantially reduced, feature propagation is strengthened. The same residual block is defined in [1] through the linear operators K 1 and K 2 , while the parameter vector Θ has three parts: Θ (1) and Θ (3) for weights W 1 and W 2 from Equation (1), respectively Θ (2) for parameters of the normalization layer N . The residual block output is defined by Equation (2), where σ is the activation function, and Y is the input vector.…”

Section: Theoretical Aspects For Pde Inspired Neural Networkmentioning

confidence: 99%

“…The residual block output is defined by Equation (2), where σ is the activation function, and Y is the input vector. The transformation of a network with several layers with ResNet blocks, input Y 0 and N layers is described in (3). F(Θ, Y) = K 2 (Θ (3) )σ(N (K 1 (Θ (1) )Y, Θ (2) ))…”

Section: Theoretical Aspects For Pde Inspired Neural Networkmentioning

confidence: 99%

“…With the outbreak of COVID-19, deep learning has been applied in various tasks: predicting the number of cases and detecting COVID-19 from the sounds of coughs or from images, either X-rays [3] or CT scans. Sciacca et al showed that the most frequent findings in the radiological data from people with COVID-19 are airspace opacities, with a predominant bilateral, peripheral, and lower zone distribution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reliable Learning with PDE-Based CNNs and DenseNets for Detecting COVID-19, Pneumonia, and Tuberculosis from Chest X-Ray Images

Marginean

Muntean

et al. 2021

Mathematics

View full text Add to dashboard Cite

It has recently been shown that the interpretation by partial differential equations (PDEs) of a class of convolutional neural networks (CNNs) supports definition of architectures such as parabolic and hyperbolic networks. These networks have provable properties regarding the stability against the perturbations of the input features. Aiming for robustness, we tackle the problem of detecting changes in chest X-ray images that may be suggestive of COVID-19 with parabolic and hyperbolic CNNs and with domain-specific transfer learning. To this end, we compile public data on patients diagnosed with COVID-19, pneumonia, and tuberculosis, along with normal chest X-ray images. The negative impact of the small number of COVID-19 images is reduced by applying transfer learning in several ways. For the parabolic and hyperbolic networks, we pretrain the networks on normal and pneumonia images and further use the obtained weights as the initializers for the networks to discriminate between COVID-19, pneumonia, tuberculosis, and normal aspects. For DenseNets, we apply transfer learning twice. First, the ImageNet pretrained weights are used to train on the CheXpert dataset, which includes 14 common radiological observations (e.g., lung opacity, cardiomegaly, fracture, support devices). Then, the weights are used to initialize the network which detects COVID-19 and the three other classes. The resulting networks are compared in terms of how well they adapt to the small number of COVID-19 images. According to our quantitative and qualitative analysis, the resulting networks are more reliable compared to those obtained by direct training on the targeted dataset.

show abstract

Missense mutations in spike protein of SARS‐CoV‐2 delta variant contribute to the alteration in viral structure and interaction with hACE2 receptor

Mahmood

Hossan

Mahmud

et al. 2022

Immunity Inflam & Disease

View full text Add to dashboard Cite

Introduction Many of the global pandemics threaten human existence over the decades among which coronavirus disease (COVID‐19) is the newest exposure circulating worldwide. The RNA encoded severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) virus is referred as the pivotal agent of this deadly disease that induces respiratory tract infection by interacting host ACE2 receptor with its spike glycoprotein. Rapidly evolving nature of this virus modified into new variants helps in perpetrating immune escape and protection against host defense mechanism. Consequently, a new isolate, delta variant originated from India is spreading perilously at a higher infection rate. Methods In this study, we focused to understand the conformational and functional significance of the missense mutations found in the spike glycoprotein of SARS‐CoV‐2 delta variant performing different computational analysis. Results From physiochemical analysis, we found that the acidic isoelectric point of the virus elevated to basic pH level due to the mutations. The targeted mutations were also found to change the interactive bonding pattern and conformational stability analyzed by the molecular dynamic's simulation. The molecular docking study also revealed that L452R and T478K mutations found in the RBD domain of delta variant spike protein contributed to alter interaction with the host ACE2 receptor. Conclusions Overall, this study provided insightful evidence to understand the morphological and attributive impact of the mutations on SARS‐CoV‐2 delta variant.

show abstract

Fast COVID-19 and Pneumonia Classification Using Chest X-ray Images

Cited by 37 publications

References 39 publications

NanoChest-Net: A Simple Convolutional Network for Radiological Studies Classification

NanoChest-Net: A Simple Convolutional Network for Radiological Studies Classification

Reliable Learning with PDE-Based CNNs and DenseNets for Detecting COVID-19, Pneumonia, and Tuberculosis from Chest X-Ray Images

Missense mutations in spike protein of SARS‐CoV‐2 delta variant contribute to the alteration in viral structure and interaction with hACE2 receptor

Contact Info

Product

Resources

About