COVID-19 classification by CCSHNet with deep fusion using transfer learning and discriminant correlation analysis

Wang, Shuihua; Nayak, Deepak Ranjan; Guttery, David S.; Zhang, Xin; Zhang, Yudong

doi:10.1016/j.inffus.2020.11.005

Cited by 209 publications

(115 citation statements)

References 54 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…There are also methods based on deep learning [ 11 , 12 ]; however, there are still aspects to be improved. In [ 13 ] authors proposed a method based on deep learning to detect COVID-19, community-acquired pneumonia and second pulmonary tuberculosis on computed tomography images. They achieved 95.61% sensitivity for COVID-19 using a two pretrained deep learning models to generate features from computer tomography images, then fuse those features using the discriminant correlation analysis (DCA) method.…”

Section: Introductionmentioning

confidence: 99%

Hyperparameter Optimization for COVID-19 Pneumonia Diagnosis Based on Chest CT

Lacerda

Barros

Albuquerque

et al. 2021

Sensors

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) have been successfully applied in the medical diagnosis of different types of diseases. However, selecting the architecture and the best set of hyperparameters among the possible combinations can be a significant challenge. The purpose of this work is to investigate the use of the Hyperband optimization algorithm in the process of optimizing a CNN applied to the diagnosis of SARS-Cov2 disease (COVID-19). The test was performed with the Optuna framework, and the optimization process aimed to optimize four hyperparameters: (1) backbone architecture, (2) the number of inception modules, (3) the number of neurons in the fully connected layers, and (4) the learning rate. CNNs were trained on 2175 computed tomography (CT) images. The CNN that was proposed by the optimization process was a VGG16 with five inception modules, 128 neurons in the two fully connected layers, and a learning rate of 0.0027. The proposed method achieved a sensitivity, precision, and accuracy of 97%, 82%, and 88%, outperforming the sensitivity of the Real-Time Polymerase Chain Reaction (RT-PCR) tests (53–88%) and the accuracy of the diagnosis performed by human experts (72%).

show abstract

Section: Introductionmentioning

confidence: 99%

Hyperparameter Optimization for COVID-19 Pneumonia Diagnosis Based on Chest CT

Lacerda

Barros

Albuquerque

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The author in [41] using a 10-fold cross-validation experiment for binary classification (normal vs. COVID-19), achieves a sensitivity of 94.44%, a specificity of 93.63%, and accuracy of 94.03%. The proposed model in [42] achieves average F1-score of 97.04 and precision of 97.32%, 96.42%, 96.99%, 97.38% on COVID-19, pneumonia, tuberculosis and healthy classes, respectively. The extractor-classifier combination in [43] achieves the best F1-score of 98.5% using MobileNet architecture with the SVM classifier and a linear Kernel.…”

Section: Results Analysis and Discussionmentioning

confidence: 97%

“…A seven-layer convolutional neural network-based COVID-19 diagnosis model has been proposed in [41] using 14-way data augmentation and introduced stochastic pooling. In reference [42] , six different pretrained models have been experimented with by making the number of layers adaptive and adding two new fully connected layers in each model. The authors have fused the features from the best two pretrained models using discriminant correlation analysis.…”

Section: Introductionmentioning

confidence: 99%

Automated detection of COVID-19 from CT scan using convolutional neural network

Mishra

Singh

Joshi

2021

Biocybernetics and Biomedical Engineering

View full text Add to dashboard Cite

Under the prevailing circumstances of the global pandemic of COVID-19, early diagnosis and accurate detection of COVID-19 through tests/screening and, subsequently, isolation of the infected people would be a proactive measure. Artificial intelligence (AI) based solutions, using Convolutional Neural Network (CNN) and exploiting the Deep Learning model’s diagnostic capabilities, have been studied in this paper. Transfer Learning approach, based on VGG16 and ResNet50 architectures, has been used to develop an algorithm to detect COVID-19 from CT scan images consisting of Healthy (Normal), COVID-19, and Pneumonia categories. This paper adopts data augmentation and fine-tuning techniques to improve and optimize the VGG16 and ResNet50 model. Further, stratified 5-fold cross-validation has been conducted to test the robustness and effectiveness of the model. The proposed model performs exceptionally well in case of binary classification (COVID-19 vs. Normal) with an average classification accuracy of more than 99% in both VGG16 and ResNet50 based models. In multiclass classification (COVID-19 vs. Normal vs. Pneumonia), the proposed model achieves an average classification accuracy of 86.74% and 88.52% using VGG16 and ResNet50 architectures as baseline, respectively. Experimental results show that the proposed model achieves superior performance and can be used for automated detection of COVID-19 from CT scans.

show abstract

“…(Private) DL ShuffleNet V2 85.40 [ 40 ] COVID-19/other pneu./healthy. (Private) 3D UNet-based network 94 [ 41 ] 284 COVID-19, 281 CAP, 293 SPT, 306 HC CCSHNet 97.04 [ 42 ] 219 COVID-19, 1345 pneumonia and 1341 normal images [ 50 ] mAlexNet + BiLSTM 98.70 [ 43 ] 361 COVID-19, 1341 Normal and 1345 Pneumonia InstaCovNet-19 99.08 Proposed method 349 COVID-19, 397 Healty CT images [ 28 ] FDEPFGN and RFINCA 95.84 …”

Section: Introductionmentioning

confidence: 99%

An automated COVID-19 detection based on fused dynamic exemplar pyramid feature extraction and hybrid feature selection using deep learning

Özyurt

Tuncer

Subaşı

2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

The new coronavirus disease known as COVID-19 is currently a pandemic that is spread out the whole world. Several methods have been presented to detect COVID-19 disease. Computer vision methods have been widely utilized to detect COVID-19 by using chest X-ray and computed tomography (CT) images. This work introduces a model for the automatic detection of COVID-19 using CT images. A novel handcrafted feature generation technique and a hybrid feature selector are used together to achieve better performance. The primary goal of the proposed framework is to achieve higher classification accuracy than convolutional neural networks (CNN) using handcrafted features of the CT images. In the proposed framework, there are four fundamental phases, which are preprocessing, fused dynamic sized exemplars based pyramid feature generation, ReliefF, and iterative neighborhood component analysis based feature selection and deep neural network classifier. In the preprocessing phase, CT images are converted into 2D matrices and resized to 256 x 256 sized images. The proposed feature generation network uses dynamic-sized exemplars and pyramid structures together. Two basic feature generation functions are used to extract statistical and textural features. The selected most informative features are forwarded to artificial neural networks (ANN) and deep neural network (DNN) for classification. ANN and DNN models achieved 94.10% and 95.84% classification accuracies respectively. The proposed fused feature generator and iterative hybrid feature selector achieved the best success rate, according to the results obtained by using CT images.

show abstract

COVID-19 classification by CCSHNet with deep fusion using transfer learning and discriminant correlation analysis

Cited by 209 publications

References 54 publications

Hyperparameter Optimization for COVID-19 Pneumonia Diagnosis Based on Chest CT

Hyperparameter Optimization for COVID-19 Pneumonia Diagnosis Based on Chest CT

Automated detection of COVID-19 from CT scan using convolutional neural network

An automated COVID-19 detection based on fused dynamic exemplar pyramid feature extraction and hybrid feature selection using deep learning

Contact Info

Product

Resources

About