ANC: Attention Network for COVID-19 Explainable Diagnosis Based on Convolutional Block Attention Module

Objective: COVID-19 is a sort of infectious disease caused by a new strain of coronavirus. This study aims to develop a more accurate COVID-19 diagnosis system.Methods: First, the n-conv module (nCM) is introduced. Then we built a 12-layer convolutional neural network (12l-CNN) as the backbone network. Afterwards, PatchShuffle was introduced to integrate with 12l-CNN as a regularization term of the loss function. Our model was named PSCNN. Moreover, multiple-way data augmentation and Grad-CAM are employed to avoid overfitting and locating lung lesions.Results: The mean and standard variation values of the seven measures of our model were 95.28 ± 1.03 (sensitivity), 95.78 ± 0.87 (specificity), 95.76 ± 0.86 (precision), 95.53 ± 0.83 (accuracy), 95.52 ± 0.83 (F1 score), 91.7 ± 1.65 (MCC), and 95.52 ± 0.83 (FMI).Conclusion: Our PSCNN is better than 10 state-of-the-art models. Further, we validate the optimal hyperparameters in our model and demonstrate the effectiveness of PatchShuffle.

show abstract

“…The dataset in this study is described in reference (15) where they provided two datasets. The first dataset is smaller.…”

Section: Dataset and Preprocessingmentioning

confidence: 99%

RETRACTED: PSCNN: PatchShuffle Convolutional Neural Network for COVID-19 Explainable Diagnosis

Wang

Zhu

Zhang

2021

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…To alleviate the overfitting and coping with the small-size dataset problem, we used the 18-way DA in (32). In their paper, X 1 = 9 different DA methods were used on both the raw image r (i) and its horizontally mirrored image r hm (i).…”

Section: Multiple-way Data Augmentationmentioning

confidence: 99%

RETRACTED: Deep Fractional Max Pooling Neural Network for COVID-19 Recognition

Wang

Satapathy

Anderson

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

Aim: Coronavirus disease 2019 (COVID-19) is a form of disease triggered by a new strain of coronavirus. This paper proposes a novel model termed “deep fractional max pooling neural network (DFMPNN)” to diagnose COVID-19 more efficiently.Methods: This 12-layer DFMPNN replaces max pooling (MP) and average pooling (AP) in ordinary neural networks with the help of a novel pooling method called “fractional max-pooling” (FMP). In addition, multiple-way data augmentation (DA) is employed to reduce overfitting. Model averaging (MA) is used to reduce randomness.Results: We ran our algorithm on a four-category dataset that contained COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis (SPT), and healthy control (HC). The 10 runs on the test set show that the micro-averaged F1 (MAF) score of our DFMPNN is 95.88%.Discussions: This proposed DFMPNN is superior to 10 state-of-the-art models. Besides, FMP outperforms traditional MP, AP, and L2-norm pooling (L2P).

show abstract

“…Similarly, Narin [ 27 ] uses the ResNet-50 model of convolutional neural network (CNN) to carry out diagnostic research. With the help of the supervised learning method based on statistical learning theory (SVM algorithm), features can be also directly extracted to determine whether the disease is present [ 32 ]. The sensitivity of their experiment is higher than that of the study in [ 26 ] and thus makes it easier for doctors to reduce the rate of missed tests.…”

Section: Intelligent Diagnosis Of Covid-19mentioning

confidence: 99%

AIoT Used for COVID-19 Pandemic Prevention and Control

Chen

Wang

et al. 2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

The pandemic of COVID-19 is continuing to wreak havoc in 2021, with at least 170 million victims around the world. Healthcare systems are overwhelmed by the large-scale virus infection. Luckily, Internet of Things (IoT) is one of the most effective paradigms in the intelligent world, in which the technology of artificial intelligence (AI), like cloud computing and big data analysis, is playing a vital role in preventing the spread of the pandemic of COVID-19. AI and 5G technologies are advancing by leaps and bounds, further strengthening the intelligence and connectivity of IoT applications, and conventional IoT has been gradually upgraded to be more powerful AI + IoT (AIoT). For example, in terms of remote screening and diagnosis of COVID-19 patients, AI technology based on machine learning and deep learning has recently upgraded medical equipment significantly and has reshaped the workflow with minimal contact with patients, so medical specialists can make clinical decisions more efficiently, providing the best protection not only to patients but also to specialists themselves. This paper reviews the latest progress made in combating COVID-19 with both IoT and AI and also provides comprehensive details on how to combat the pandemic of COVID-19 as well as the technologies that may be applied in the future.

show abstract

ANC: Attention Network for COVID-19 Explainable Diagnosis Based on Convolutional Block Attention Module

Cited by 41 publications

References 36 publications

RETRACTED: PSCNN: PatchShuffle Convolutional Neural Network for COVID-19 Explainable Diagnosis

RETRACTED: PSCNN: PatchShuffle Convolutional Neural Network for COVID-19 Explainable Diagnosis

RETRACTED: Deep Fractional Max Pooling Neural Network for COVID-19 Recognition

AIoT Used for COVID-19 Pandemic Prevention and Control

Contact Info

Product

Resources

About