Deep Learning Algorithms for Automatic COVID-19 Detection on Chest X-Ray Images

Cannata, Sergio; Paviglianiti, Annunziata; Pasero, Eros; Cirrincione, Giansalvo; Cirrincione, Maurizio

doi:10.1109/access.2022.3221531

Cited by 8 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Manickam et al [14] aimed at detecting pneumonia using deep learning models. They used the ResNet50 [15] InceptionV3 and InceptionResNetV2 models and preprocessing steps were performed to improve performance. The best results were obtained using the ResNet50 model with 93.06% accuracy.…”

Section: Related Workmentioning

confidence: 99%

Enhanced Pneumonia Diagnosis Using Chest X-Ray Image Features and Multilayer Perceptron and k-NN Machine Learning Algorithms

Çelik¹,

Demi̇rel²

2023

View full text Add to dashboard Cite

Pneumonia poses a significant risk of mortality, particularly in individuals with compromised immune systems, necessitating early diagnosis and treatment to combat the disease effectively. In this study, we employed Multilayer Perceptron (MLP) and k-Nearest Neighbors (k-NN) machine learning (ML) algorithms to facilitate pneumonia diagnosis using preprocessed Chest X-ray images. Preprocessing steps, including Histogram Equalization, Mask R-CNN (Mask Region-Based Convolutional Neural Network), and Otsu thresholding, were successively performed on the images. Textural features were subsequently extracted from the Chest X-ray images and utilized as inputs for the classification algorithms. To address the imbalanced class problem in the training data, the Synthetic Minority Over-sampling Technique (SMOTE) was implemented. Classification evaluation metrics included accuracy, precision, recall, F1-Score, and AUC Score (Area Under Curve Score). The results revealed that the MLP algorithm outperformed the k-NN algorithm across all metrics. Furthermore, a comparison of the MLP and k-NN algorithms with previous studies in the literature demonstrated the superiority of the MLP algorithm, achieving an accuracy of 95.673%, F1-Score of 95.706%, and AUC Score of 99.006%. This study highlights the potential of employing the MLP algorithm for highly accurate pneumonia diagnosis using Chest X-ray images.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhanced Pneumonia Diagnosis Using Chest X-Ray Image Features and Multilayer Perceptron and k-NN Machine Learning Algorithms

Çelik¹,

Demi̇rel²

2023

View full text Add to dashboard Cite

show abstract

“…This can also be observed in research that addresses the diagnosis of COVID-19. Many works are found based on pre-trained model with transfer learning using known networks: AlexNet [38], MobileNetV2 [8,[20][21]31], NASNet [11], Inception -V3 [8,25], DarkNet -53 [28], DenseNet -121 [9,11,17,25,39], DenseNet -201 [8,14,21], DenseNet -210 [38], Inception -V4 [31], InceptionResNet -V2 [8,31], ReconNet [25], ResNet -8 [18], ResNet16 [18], ResNet -18 [14-15, 17, 27, 37-38], ResNet -50 [8,13,15,22,24,29,41], ResNet -101 [17], Xception [8,11], EfficientNet [11], SqueezeNet [14][15]20], VGG -16 [10-13, 17, 27, 31, 40], VGG -19 [8,30]. Works employing custom CNNs are also available [8,10,19,25,…”

Section: Introductionmentioning

confidence: 99%

Computational Intelligence Conceptions to Automated Diagnosis: Feature Grouping for Performance Improvement

Nascimento,

Saraiva Junior,

Faria

et al. 2023

Braz. arch. biol. technol.

View full text Add to dashboard Cite

The motivation of this work is to investigate two technological AI paths, evaluate the performance, and discuss the results. Using a covid-19 chest X-ray images databank, we address the two distinct experiments to this problem: (1) an investigation of feature extraction and classification using machine learning algorithms and (2) an approach based on transfer learning used in state-of-the-art applications. For the implementation of our proposal (1), an integrated framework consisting of 25 algorithms with different characteristics was developed to extract features from chest X-ray images. Following this path, we seek to focus on the spatial spectral signatures of shape, texture, local and global statistical quantities. The extraction of features based on information in Fourier and wavelet space-frequency domain was also implemented as part of the framework. On the other hand, several transfer learning CNN's were also used to evaluate performance and to compere to the first technological path results. Furthermore, the performance of other results reported by various other works are provided. The comparative performance evaluation demonstrated that the two concepts for a computational intelligence tool can produce very good results even working in high-dimensional vector spaces. HIGHLIGHTS• An integrated framework for feature extraction in medical images is proposed.• It is investigated the automatic diagnosis in chest X-ray images using several algorithms.• It is show that performance is increased when different feature extraction algorithms are merged.• Experiments were performed with fourteen different IA algorithms and the results were compared.

show abstract

“…Sensors 2023,23, x FOR PEER REVIEW 9 of 31 a subsequent dense layer of 256 units, a dropout layer, a subsequent dense layer of 128 units, and a further dropout layer were added. On the final layer, SoftMax activation was used, and data classification resulted in an output of size equal to class number in different classification schemes.…”

mentioning

confidence: 99%

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning

Sultana

Nahiduzzaman

Bakchy

et al. 2023

Sensors

View full text Add to dashboard Cite

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.

show abstract

Deep Learning Algorithms for Automatic COVID-19 Detection on Chest X-Ray Images

Cited by 8 publications

References 27 publications

Enhanced Pneumonia Diagnosis Using Chest X-Ray Image Features and Multilayer Perceptron and k-NN Machine Learning Algorithms

Enhanced Pneumonia Diagnosis Using Chest X-Ray Image Features and Multilayer Perceptron and k-NN Machine Learning Algorithms

Computational Intelligence Conceptions to Automated Diagnosis: Feature Grouping for Performance Improvement

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning

Contact Info

Product

Resources

About