A dual-stage deep convolutional neural network for automatic diagnosis of COVID-19 and pneumonia from chest CT images

Sadik, Farhan; Dastider, Ankan Ghosh; Subah, Mohseu Rashid; Mahmud, Tanvir; Fattah, Shaikh Anowarul

doi:10.1016/j.compbiomed.2022.105806

Cited by 12 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Farhan Sadik et al [20] proposed a modified version of the DenseNet architecture called P-DenseCOVNet for efficient feature extraction and the diagnosis of COVID-19 and pneumonia from segmented lung slices. This innovative design incorporates parallel convolutional routes alongside the traditional DenseNet model to enhance performance by addressing positional arguments.…”

Section: Background Workmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model

Arulananth,

Prakash,

Ayyasamy

et al. 2024

IEEE Access

View full text Add to dashboard Cite

There is a substantial worldwide effect, both in terms of disease and death, that is caused by pediatric pneumonia, which is a disorder that affects children under the age of five. Even while Streptococcus pneumoniae is the most prevalent agent responsible for this sickness, it may also be brought on by other bacteria, viruses, or fungi. An efficient approach utilizing deep-learning methods to forecast pediatric pneumonia reliably using chest X-ray images has been developed. The current study presents an updated version of the DenseNet-121 deep-learning model developed for identifying scans of pediatric pneumonia. The batch normalization, maximum pooling, and dropout layers introduced into the standard model were done so to improve its accuracy. The activations of the preceding layers are scaled and normalized using batch normalization, leading to a mean value of zero and a variance of one. This helps to decrease internal variability during training, which in turn speeds up the training process, promotes model stability, and improves the model's overall capacity to generalize. Max pooling is a beneficial technique for cutting down on the number of model parameters, making the model more computationally effective. Meanwhile, dropout is a preventative measure against overfitting by decreasing the co-dependence of neurons. As a result, the network acquires more durable and adaptive features. Classifying instances of pediatric pneumonia with the help of the proposed model resulted in an exceptional accuracy rate of 97.03%.

show abstract

Section: Background Workmentioning

confidence: 99%

“…Figure 9 demonstrates that the suggested DenseNet-121 requires 989 seconds to finish the training phase, while the existing methods [18,19,20,21,26,27] -The values of the evaluation parameters are shown in Table 1, with Precision set to 0.965 for both classes and Sensitivity and Specificity set to 1 for both classes.…”

Section: Vgg-16mentioning

confidence: 99%

Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model

Arulananth,

Prakash,

Ayyasamy

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Sadik et al [ 172 ] propose a new paradigm for COVID-19 detection using customized U-Net. Computer-aided diagnostic technologies are becoming increasingly necessary in the Coronavirus disease-2019 (COVID-19) outbreak for the quick and reliable detection of a significant amount of individuals in addition to conventional approaches.…”

Section: Deep Learning For Medical Image Analysis and Cadmentioning

confidence: 99%

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Iqbal

Qureshi

et al. 2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of Neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

show abstract

“…In addition, Khan et al [ 23 ] performed a multi classification test on chest radiographs using CoroNet, which was trained and tested on a finite dataset consisting of a few hundred images, and achieved a an overall accuracy of 89.6% and an accuracy of 93%. Farhan et al [ 24 ] proposed a model called SKICU-Net, which was designed to overcome the loss of information in dimension scaling by adding an extra hopping interconnection to the U-Net model. In addition, they introduced parallel convolution paths to a traditional DenseNet model to obtain a classification model.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans

Wen¹,

Liu²,

Liu³

et al. 2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

A dual-stage deep convolutional neural network for automatic diagnosis of COVID-19 and pneumonia from chest CT images

Cited by 12 publications

References 41 publications

Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model

Classification of Paediatric Pneumonia Using Modified DenseNet-121 Deep-Learning Model

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans

Contact Info

Product

Resources

About