Deep Learning Models for Classification and Localization of COVID-19 Abnormalities on Chest Radiographs

Muhammad, L. J.; Amshi, Jamila Musa; Usman, Sani Sharif; Badi, Ibrahim; Mohammed, I. A.; Dada, O. S.; Haruna, Ahmed Abba

doi:10.1109/iccis54243.2021.9676401

Cited by 6 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The convolutional layer shares a lot of weight while the composite layers soften the convolutional layer release and reduce the amount of data rate from the lower layer [12]. The sharing of weight in the convolutional layer together with appropriate chosen pooling schemes, endows the CNN with some invariance properties [7,[22][23][24].CNN has been found to be one of the most effective DL vision algorithms used for image recognition and computer vision [25,26]. In CNN's convolutional layer, convolutional features mapping from previous layer are convolved with learnable kernels with non-linear or linear activation functions such as hyperbolic tangent, sigmoid, softmax among others to output feature maps [27,28].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…However, many of the mutations of the variants are innocuous on how the SARS-CoV-2 affects humans. Nevertheless, the mutations of others variants such as genetic changes in delta variants, is often made the SARS-CoV-2 more transmissible, contagious than its original version of the virus discovered in late 2019 [7,8].…”

Section: Introductionmentioning

confidence: 99%

“…The variant was first reported on 24th November, 2021 in South Africa from the specimen collected on 9th November, 2021 in the country. On 26th November, 2021 WHO designed the variant as the "variant of concern" (VOC), named Omicron, due to how easily the variant spreads, severity of illness it causes to humans and its ability to cause a higher risk of reinfection as compared to other previously identified and reported variants [7]. Therefore, WHO has called on countries to develop monitoring and follow-up efforts to better understand the transmission of the new variant, to report cases the variant, to submit complete genetic sequences and related metadata to public and multilateral websites and to co-operate with the international community accordingly, conduct laboratory tests and field investigations to understand the potential impact of the new mutation on COVID19 epidemiology, social and effective community health measures, sensitivity, diagnostic techniques and methods, antibody neutrality, immune responses and appropriate traits [7,9].…”

Section: Introductionmentioning

confidence: 99%

“…On 26th November, 2021 WHO designed the variant as the "variant of concern" (VOC), named Omicron, due to how easily the variant spreads, severity of illness it causes to humans and its ability to cause a higher risk of reinfection as compared to other previously identified and reported variants [7]. Therefore, WHO has called on countries to develop monitoring and follow-up efforts to better understand the transmission of the new variant, to report cases the variant, to submit complete genetic sequences and related metadata to public and multilateral websites and to co-operate with the international community accordingly, conduct laboratory tests and field investigations to understand the potential impact of the new mutation on COVID19 epidemiology, social and effective community health measures, sensitivity, diagnostic techniques and methods, antibody neutrality, immune responses and appropriate traits [7,9]. WHO also asked individual to take measures to reduce the risk of the new variant to the barest minimum especially social and public health measures such as hand hygiene, wearing well-fitting mask, improving ventilation of indoor space, getting vaccinated, physical distance and avoiding crowded spaces, among others.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

CNN-LSTM deep learning based forecasting model for COVID-19 infection cases in Nigeria, South Africa and Botswana

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background COVID-19 pandemic has indeed plunged the global community especially African countries into an alarming difficult situation culminating into a great deal amounts of catastrophes such as economic recession, political instability and loss of jobs. The pandemic spreads exponentially and causes loss of lives. Following the outbreak of the omicron new variant of concern, forecasting and identification of the COVID-19 infection cases is very vital for government at various levels. Hence, having knowledge of the spread at a particular point in time, swift actions can be taken by government at various levels with a view to accordingly formulate new policies and modalities towards minimizing the trajectory of the consequences of COVID-19 pandemic to both public health and economic sectors. Methods Here, a potent combination of Convolutional Neural Network (CNN) learning algorithm along with Long Short Term Memory (LSTM) learning algorithm has been proposed in this work in order to produce a hybrid of a deep learning algorithm Convolutional Neural Network -Long Short Term Memory (CNN-LSTM) for forecasting COVID-19 infection cases particularly in Nigeria, South Africa and Botswana. Forecasting models for COVID-19 infection cases in Nigeria, South Africa and Botswana, were developed for 10 days using deep learning-based approaches namely CNN, LSTM and CNN-LSTM deep learning algorithm respectively. Results The models were evaluated on the basis of four standard performance evaluation metrics which include accuracy, MSE, MAE and RMSE respectively. However, the CNN-LSTM deep learning-based forecasting model achieved the best accuracy of 98.30%, 97.60%, and 97.74% for Nigeria, South Africa and Botswana respectively; and in the same manner, achieved lesser MSE, MAE and RMSE values compared to models developed with CNN and LSTM respectively. Conclusions Taken together, the CNN-LSTM deep learning-based forecasting model for COVID-19 infection cases in Nigeria, South Africa and Botswana dramatically surpasses the two other DL based forecasting models (CNN and LSTM) for COVID-19 infection cases in Nigeria, South Africa and Botswana in terms of not only the best accuracy of with 98.30%, 97.60%, and 97.74% but also in terms of lesser MSE, MAE and RMSE.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CNN-LSTM deep learning based forecasting model for COVID-19 infection cases in Nigeria, South Africa and Botswana

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…2.4. Regional Convolutional Neural networks(RCNNs) R-CNN [15] includes variants like Fast R-CNN and Faster R-CNN, can be used in the detection of lung infections in medical images [16], [17], [18], [19] including chest X-rays (CXR) and computed tomography (CT) scans. Here's an overview of how R-CNNs can be applied to this task.…”

Section: Vision Transformersmentioning

confidence: 99%

Lung Infection Detection using Contemporary Techniques of Artificial Intellligence

Koyyada,

Rawat,

Singh

2022

CJACSIT

View full text Add to dashboard Cite

Lung diseases are increasing day by day when compared to other diseases. The world has been experiencing COVID-19 since 2020 and one has no answer how to cure it in the initial days. Near future majority of the humanity will suffer from lung diseases based on studies. In this context, we are exploring contemporary artificial techniques (AI) and explaining how these will help in detecting the disease. Among Convolutional neural nets (CNNs), Regional Convolutional neural nets (RCNNs), and Vision Transformers (VT) state-of-the-art methods. The techniques are very diversified from the concept point of view. Each carries out the process in an expert wise. One who wants to automate the process can make an ensemble of these models.

show abstract

Learning Features Using an optimized Artificial Neural Network for Breast Cancer Diagnosis

Al-Shourbaji

Kachare²,

Zogaan

et al. 2022

SN COMPUT. SCI.

View full text Add to dashboard Cite

Deep Learning Models for Classification and Localization of COVID-19 Abnormalities on Chest Radiographs

Cited by 6 publications

References 22 publications

CNN-LSTM deep learning based forecasting model for COVID-19 infection cases in Nigeria, South Africa and Botswana

CNN-LSTM deep learning based forecasting model for COVID-19 infection cases in Nigeria, South Africa and Botswana

Lung Infection Detection using Contemporary Techniques of Artificial Intellligence

Learning Features Using an optimized Artificial Neural Network for Breast Cancer Diagnosis

Contact Info

Product

Resources

About