A noise robust convolutional neural network for image classification

Momeny, Mohammad; Latif, Ali Mohammad; Sarram, Mehdi Agha; Sheikhpour, Razieh; Zhang, Yudong

doi:10.1016/j.rineng.2021.100225

Cited by 82 publications

(28 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Typically, noise-based data augmentation in DL is performed when there is a possibility of image data being corrupted by noise [ 16 ]. Data augmentation by noise addition is a strategy that improves the robustness and generalization of CNNs [ [17] , [18] , [19] , [20] , [21] , [22] , [23] , [24] ]. Moreno-Barea et al [ 21 ] tested the noise injection to images from a Gaussian distribution, and showed it to be useful for improving CNN-based classification performance [ 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images

Momeny

Neshat

Hussain

et al. 2021

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

Chest X-ray images are used in deep convolutional neural networks for the detection of COVID-19, the greatest human challenge of the 21st century. Robustness to noise and improvement of generalization are the major challenges in designing these networks. In this paper, we introduce a strategy for data augmentation using the determination of the type and value of noise density to improve the robustness and generalization of deep CNNs for COVID-19 detection. Firstly, we present a learning-to-augment approach that generates new noisy variants of the original image data with optimized noise density. We apply a Bayesian optimization technique to control and choose the optimal noise type and its parameters. Secondly, we propose a novel data augmentation strategy, based on denoised X-ray images, that uses the distance between denoised and original pixels to generate new data. We develop an autoencoder model to create new data using denoised images corrupted by the Gaussian and impulse noise. A database of chest X-ray images, containing COVID-19 positive, healthy, and non-COVID pneumonia cases, is used to fine-tune the pre-trained networks (AlexNet, ShuffleNet, ResNet18, and GoogleNet). The proposed method performs better results compared to the state-of-the-art learning to augment strategies in terms of sensitivity (0.808), specificity (0.915), and F-Measure (0.737). The source code of the proposed method is available at https://github.com/mohamadmomeny/Learning-to-augment-strategy .

show abstract

Section: Introductionmentioning

confidence: 99%

Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images

Momeny

Neshat

Hussain

et al. 2021

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…8 c that if the pixel value in the resized image is taken from the central pixel of the corresponding

88

block, then noisy pixel values from the original image are easily passed to the resized image. To avoid this issue, we adopt the adaptive resizing [27] technique, where noisy pixel values do not get passed to the resized image ( Fig. 8 d).…”

Section: Methodsmentioning

confidence: 99%

“…Typically, a new feature map

is generated by a convolution layer of a CNN as [29] :

where

is the location coordinate of the k th kernel,

is the input image/feature patch,

is the learned weight matrix of the k th convolution kernel, and

is the bias of the convolution layer. In this paper, we modify the conventional convolution layer of a CNN to make it more robust to noise by incorporating our noise-map

as [27] :

…”

Section: Methodsmentioning

confidence: 99%

“…This approach showed an increase in peak signal-to-noise ratio (PSNR) of 1.2 dB in the restored medical images compared to the noisy counterparts. The classification performance of a CNN gets deteriorated, when input images are corrupted by the impulse noise [27] . Preprocessing input images to remove noise before feeding to a CNN usually improves the classification performance of the CNN.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning-to-augment incorporated noise-robust deep CNN for detection of COVID-19 in noisy X-ray images

Akbarimajd

Hoertel

Hussain

et al. 2022

Journal of Computational Science

Self Cite

View full text Add to dashboard Cite

“…Noisy images reduce the classification performance of convolutional neural networks and increase the training time of the networks. In this paper, a Noise-Robust Convolutional Neural Network (NR-CNN) is proposed by author(s) to classify the noisy images without any preprocessing for noise removal and improve the classification performance of noisy images in convolutional neural networks [15]. But, to get blur-free images with exact identification of pixel sets, CNN can be modified.…”

Section: Methodsmentioning

confidence: 99%

Development of the new Aquicnn algorithm for an augmentation of CT scans images for COVID-19 Patients

Jadhav¹

2022

Journal of Pharmaceutical Negative Results

View full text Add to dashboard Cite

The world is restoring life balance after the global Covid-19 pandemic. This situation, giving birth to new problems, arose as an outcome of pre-and post pandemic scenarios. Healthcare system was under tremendous burden during this pandemic. Government bodies, scientists, drug discovery and drug registration were working in cooperation to fight the situation and to save lives. Out of all such activities, one healthcare domain is a key player, and that is the radiological department of hospitals. As discovery made those Covid-19 effects on lungs, the pressure on CT scan activities rose. To generate a CT scan quickly and to diagnose lung condition is the need of hour. Furthermore, that became a challenge for early detection of lung conditions. Hence, this paper presents the proposed research to develop iterative techniques using deep learning computation. Paper presents the proposed lung image acquisition and augmentation algorithm developed using a convolution neural network named “AquiCNN”. This proposed algorithm will be useful for quick and enhanced lung CT image analysis.

show abstract

A noise robust convolutional neural network for image classification

Cited by 82 publications

References 35 publications

Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images

Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images

Learning-to-augment incorporated noise-robust deep CNN for detection of COVID-19 in noisy X-ray images

Development of the new Aquicnn algorithm for an augmentation of CT scans images for COVID-19 Patients

Contact Info

Product

Resources

About