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

Akbarimajd, Adel; Hoertel, Nicolas; Hussain, Munira; Neshat, Ali Asghar; Marhamati, Mahmoud; Bakhtoor, Mahdi; Momeny, Mohammad

doi:10.1016/j.jocs.2022.101763

Cited by 36 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Monkeypox is commonly diagnosed using the polymerase chain reaction (PCR) technique or skin lesion test by electron microscope (Laboratory test). The most reliable approach for detecting viruses is PCR, and it has recently been used to diagnose COVID-19 [15,16]. Furthermore, bio-inspired PSO-based approaches may assist in the identi cation of viruses through digital image processing and analysis.…”

Section: Introductionmentioning

confidence: 99%

Usage of Particle Swarm Optimization in Digital Images Selection for Monkeypox Virus Prediction and Diagnosis

Mandal

2023

Preprint

View full text Add to dashboard Cite

Identifying skin diseases by using digital images of skin that are also automated, efficient, and accurate is essential for biomedical image analysis. Many researchers have developed numerous machine-learning techniques for the prediction and diagnosis of various diseases that help clinicians identify infections early and provide crucial data for virus management. In this work, we use the inherent attributes of PSO, such as exploration and exploitation, to identify images for monkeypox virus prediction and diagnosis. Alongside, monkeypox, chickenpox, smallpox, cowpox, measles, tomato flu, and normal skin images were all considered in this study for monkeypox virus prediction and diagnosis. We collect photos from the International Skin Imaging Collaboration (ISIC) for analysis and experimentation purposes. Finally, we compare the proposed model PSOMPX for monkeypox virus identification with four distinct pre-trained deep learning models (e.g., VGG16 [29], ResNet50 [29], InceptionV3 [31], and Ensemble [30]), and the classifier hidden Markov model along with the GLCM-SVM is used in the diagnostic test to separate monkeypox skin lesions from other skin infections. The four performance evaluation metrics—accuracy, precision, recall, and F1 score—evaluate the model and analyze the outcomes of experiments. Finally, the experimental results obtained through the PSOMPX model significantly outperformed other models due to its numerous traits, with a total accuracy of 90.01% (F1-Score: 85.87%) achieved.

show abstract

Section: Introductionmentioning

confidence: 99%

Usage of Particle Swarm Optimization in Digital Images Selection for Monkeypox Virus Prediction and Diagnosis

Mandal

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This has made neural networks, and derivatives such as convolutional neural networks, prevalent in the field of data analysis and they have been successfully applied on spectral information 1,25,26 . Another significant advantage of neural networks is their adaptability to noise in the data and variations in the signal background 1,27 . However, these methods often require several thousand examples to learn from and these examples have to be rigorously curated to avoid biasing the model.…”

Section: Introductionmentioning

confidence: 99%

Identification of extracellular vesicles from theirRaman spectra via self-supervised learning

Jensen,

Guerreiro,

Enciso-Martinez

et al. 2023

Preprint

View full text Add to dashboard Cite

Extracellular vesicles (EVs) released from cells attract interest for their possible role in health and diseases. The detection and characterization of EVs is challenging due to the lack of specialized methodologies. Raman spectroscopy, however, has been suggested as a novel approach for biochemical analysis of EVs. To extract information from the spectra, a novel deep learning architecture is explored as a versatile variant of autoencoders. The proposed architecture considers the frequency range separately from the intensity of the spectra. This enables the model to adapt to the frequency range, rather than requiring that all spectra be pre-processed to the same frequency range as it was trained on. It is demonstrated that the proposed architecture accepts Raman spectra of EVs and lipoproteins from 13 biological sources and from two laboratories. High reconstruction accuracy is maintained despite large variances in frequency range and noise level. It is also shown that the architecture is able to cluster the biological nanoparticles by their Raman spectra and differentiate them by their origin without pre-processingof the spectra or supervision during learning. The model performs label-free differentiation, including separating EVs from activated vs. non-activated blood platelets and EVs/lipoproteins from prostate cancer patients vs. non-cancer controls. The differentiation is evaluated by creating a neural network classifier that observes the features extracted by the model to classify the samples according to their origin. The classification reveals a test sensitivity of 92.2% and selectivity of 92.3% over 769 measurements from two labs that have different measurement configurations.

show abstract

“…Previous studies conducted by Mohammad Momeny (2021), titled "A noise-robust convolutional neural network for image classification" [14], elucidates the process of noise reduction in image data without relying on preprocessing. Similarly, another study by Adel Akbarimajd (2022), titled "Learning-to-augment incorporated noise-robust deep CNN for detection of COVID-19 in noisy X-ray images" [15], shares a parallel focus and employs the same approach by utilizing a Noise-Robust Convolutional Neural Network. Building upon the foundation laid by these prior investigations, this study employs CNN architectures, specifically VGG16 and ResNet 50, to assess the resilience of both architectures in classifying images degraded by Gaussian noise.…”

Section: Introductionmentioning

confidence: 99%

Robust Convolutional Neural Network for Image Classification with Gaussian Noise

Surono,

Arofah,

Thobirin

2023

Fuzzy Systems and Data Mining IX

View full text Add to dashboard Cite

A Convolutional Neural Network (CNN) is one branch of Deep Learning widely used for image classification. CNN have complex architectures and capable of achieving high accuracy and producing good results. However, CNN have limitations, especially when dealing with noisy images. Image noise can decrease classification performance and increase network training time. This research was tested the robustness of two CNN methods, namely VGG16 and ResNet50, in processing images with added Gaussian noise at various levels, without any preprocessing. The dataset used is the Rice Image Dataset, which consists of images of 5 different types of rice. The data is divided into three parts: 70% for training, 20% for testing, and 10% for validation. The results of this study show that as the variability in generating Gaussian noise in the images increases, the loss function value consistently increases, and the accuracy decreases. However, the increase in the loss function value and the decrease in accuracy are not significantly different among the different levels of noise variability.

show abstract

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

Cited by 36 publications

References 43 publications

Usage of Particle Swarm Optimization in Digital Images Selection for Monkeypox Virus Prediction and Diagnosis

Usage of Particle Swarm Optimization in Digital Images Selection for Monkeypox Virus Prediction and Diagnosis

Identification of extracellular vesicles from theirRaman spectra via self-supervised learning

Robust Convolutional Neural Network for Image Classification with Gaussian Noise

Contact Info

Product

Resources

About