Classification of Lung Opacity, COVID-19, and Pneumonia from Chest Radiography Images Based on Convolutional Neural Networks

Wibowo, Ferry Wahyu; Wihayati,

doi:10.1109/isriti54043.2021.9702841

Cited by 4 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset consists of ten chest X-ray images, each characterized by a specific number of images. Notably, the "Normal" class contains 13,953 images and is collected from labeled datasets [22,23,26,27,29,36]. Additionally, the "Tuberculosis" class includes 5242 images and is sourced from datasets [22,30,32,36], while "Lung Opacity" consists of 7236 images drawn from datasets [24,29].…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…Notably, the "Normal" class contains 13,953 images and is collected from labeled datasets [22,23,26,27,29,36]. Additionally, the "Tuberculosis" class includes 5242 images and is sourced from datasets [22,30,32,36], while "Lung Opacity" consists of 7236 images drawn from datasets [24,29]. A total of 11,566 images from datasets [24,26,27,29,31] make up the "COVID-19" class, and 11,683 images from datasets [23,24,26,32] make up "Pneumonia".…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…Additionally, the "Tuberculosis" class includes 5242 images and is sourced from datasets [22,30,32,36], while "Lung Opacity" consists of 7236 images drawn from datasets [24,29]. A total of 11,566 images from datasets [24,26,27,29,31] make up the "COVID-19" class, and 11,683 images from datasets [23,24,26,32] make up "Pneumonia". The "Pneumothorax" class comprises 6148 images gathered from datasets [25,33,37], and "Nodules" includes 4131 images from datasets [25,28,38].…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…In this study, we established one of the most extensive publicly available datasets [22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38], containing 17 datasets of chest X-ray images sourced from GitHub, Kaggle, Mendeley Data, and the National Institutes of Health (NIH) Clinical Centre. The ten disease categories in the large data hub are normal, effusion, pulmonary fibrosis, lung opacity, mass, nodule, COVID-19, pneumonia, pneumothorax, and tuberculosis.…”

Section: Introductionmentioning

confidence: 99%

“…[22,23,26,27,29,36] 2 Tuberculosis 5242 [22,30,32,36] 3 Lung Opacity 7212 [24,29] 4 COVID-19 11,566 [24,26,27,29,31] 5 Pneumonia 11,683 [23,24,26,32]…”

mentioning

confidence: 99%

See 4 more Smart Citations

DeepChestGNN: A Comprehensive Framework for Enhanced Lung Disease Identification through Advanced Graphical Deep Features

Rana,

Hosen,

Tonni

et al. 2024

Sensors

View full text Add to dashboard Cite

Lung diseases are the third-leading cause of mortality in the world. Due to compromised lung function, respiratory difficulties, and physiological complications, lung disease brought on by toxic substances, pollution, infections, or smoking results in millions of deaths every year. Chest X-ray images pose a challenge for classification due to their visual similarity, leading to confusion among radiologists. To imitate those issues, we created an automated system with a large data hub that contains 17 datasets of chest X-ray images for a total of 71,096, and we aim to classify ten different disease classes. For combining various resources, our large datasets contain noise and annotations, class imbalances, data redundancy, etc. We conducted several image pre-processing techniques to eliminate noise and artifacts from images, such as resizing, de-annotation, CLAHE, and filtering. The elastic deformation augmentation technique also generates a balanced dataset. Then, we developed DeepChestGNN, a novel medical image classification model utilizing a deep convolutional neural network (DCNN) to extract 100 significant deep features indicative of various lung diseases. This model, incorporating Batch Normalization, MaxPooling, and Dropout layers, achieved a remarkable 99.74% accuracy in extensive trials. By combining graph neural networks (GNNs) with feedforward layers, the architecture is very flexible when it comes to working with graph data for accurate lung disease classification. This study highlights the significant impact of combining advanced research with clinical application potential in diagnosing lung diseases, providing an optimal framework for precise and efficient disease identification and classification.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…[22,23,26,27,29,36] 2 Tuberculosis 5242 [22,30,32,36] 3 Lung Opacity 7212 [24,29] 4 COVID-19 11,566 [24,26,27,29,31] 5 Pneumonia 11,683 [23,24,26,32]…”

mentioning

confidence: 99%

See 3 more Smart Citations