Chest X-ray analysis empowered with deep learning: A systematic review

Applied Soft Computing, Journal Year: 2022, Volume and Issue: 126, P. 109319 - 109319

Published: July 18, 2022

Language: Английский

---

AI-driven deep CNN approach for multi-label pathology classification using chest X-Rays

PeerJ Computer Science, Journal Year: 2021, Volume and Issue: 7, P. e495 - e495

Published: April 20, 2021

Artificial intelligence (AI) has played a significant role in image analysis and feature extraction, applied to detect diagnose wide range of chest-related diseases. Although several researchers have used current state-of-the-art approaches produced impressive clinical outcomes, specific techniques may not contribute many advantages if one type disease is detected without the rest being identified. Those who tried identify multiple diseases were ineffective due insufficient data available balanced. This research provides contribution healthcare industry community by proposing synthetic augmentation three deep Convolutional Neural Networks (CNNs) architectures for detection 14 The employed models are DenseNet121, InceptionResNetV2, ResNet152V2; after training validation, an average ROC-AUC score 0.80 was obtained competitive as compared previous that trained multi-class classification anomalies x-ray images. illustrates how proposed model practices neural networks classify with better accuracy.

Language: Английский

---

Intelligent Pneumonia Identification From Chest X-Rays: A Systematic Literature Review

IEEE Access, Journal Year: 2021, Volume and Issue: 9, P. 51747 - 51771

Published: Jan. 1, 2021

Chest radiography is a significant diagnostic tool used to detect diseases afflicting the chest. The automatic detection techniques associated with computer vision are being adopted in medical imaging research. Over last decade, several remarkable advancements have been made field of diagnostics application deep learning techniques. Various automated systems proposed for rapid pneumonia from chest X-rays. Although algorithms currently available detection, detailed review summarizing literature and offering guidelines practitioners lacking. This study will help select most effective efficient methods real-time perspective, datasets, understand results obtained this domain. It also present an overview on intelligent identification usability, goodness factors, computational complexities employed analyzed. Additionally, discusses quality, size X-ray datasets coping unbalanced datasets. A comparison studies reveals that majority applied highly limited, providing unreliable rendering unsuitable large-scale use. Large-scale balanced can be via smart techniques, such as generative adversarial networks. Current has indicated learning-based achieve best classification accuracy 98.7%, sensitivity 0.99, specificity 0.98. higher offered by deep-learning addition their appropriate class balancing serves good reference further

Language: Английский

---

Pneumonia Detection Proposing a Hybrid Deep Convolutional Neural Network Based on Two Parallel Visual Geometry Group Architectures and Machine Learning Classifiers

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 62110 - 62128

Published: Jan. 1, 2022

Pneumonia is an acute respiratory infection that has led to significant deaths of people worldwide. This lung disease more common in older than 65 and children under five years old. Although the treatment pneumonia can be challenging, it prevented by early diagnosis using Computer-Aided Diagnosis (CAD) systems. Chest X-Rays (CXRs) are currently primary imaging tool for detection pneumonia, which widely used radiologists. While standard approach detecting based on clinicians' decisions, various Deep Learning (DL) methods have been developed considering CAD system. In this regard, a novel hybrid Convolutional Neural Network (CNN) model proposed three classification approaches. first approach, Fully-Connected (FC) layers utilized CXR images. trained several epochs weights result highest accuracy saved. second optimized extract most representative image features Machine (ML) classifiers employed classify third ensemble created The results suggest classifier Support Vector (SVM) with Radial Basis Function (RBF) Logistic Regression (LR) best performance 98.55% accuracy. Ultimately, deployed create web-based system assist radiologists

Language: Английский

---

RETRACTED ARTICLE: Automatic lung disease classification from the chest X-ray images using hybrid deep learning algorithm

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 82(25), P. 38561 - 38587

Published: March 22, 2023

Language: Английский

---

Joint Diagnosis of Pneumonia, COVID-19, and Tuberculosis from Chest X-ray Images: A Deep Learning Approach

Diagnostics, Journal Year: 2023, Volume and Issue: 13(15), P. 2562 - 2562

Published: Aug. 1, 2023

Pneumonia, COVID-19, and tuberculosis are some of the most fatal common lung diseases in current era. Several approaches have been proposed literature for diagnosis individual diseases, since each requires a different feature set altogether, but few studies joint diagnosis. A patient being diagnosed with one disease as negative may be suffering from other disease, vice versa. However, said related to lungs, there might likelihood more than present same patient. In this study, deep learning model that is able detect mentioned chest X-ray images patients proposed. To evaluate performance model, multiple public datasets obtained Kaggle. Consequently, achieved 98.72% accuracy all classes general recall score 99.66% 99.35% No-findings, 98.10% Tuberculosis, 96.27% respectively. Furthermore, was tested using unseen data augmented dataset proven better state-of-the-art terms metrics.

Language: Английский

---

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

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 35716 - 35727

Published: Jan. 1, 2024

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

Language: Английский

---

A novel ensemble learning framework based on a genetic algorithm for the classification of pneumonia

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 133, P. 108494 - 108494

Published: May 2, 2024

Language: Английский

---

A comparative study of multiple neural network for detection of COVID-19 on chest X-ray

EURASIP Journal on Advances in Signal Processing, Journal Year: 2021, Volume and Issue: 2021(1)

Published: July 27, 2021

Abstract Coronavirus disease of 2019 or COVID-19 is a rapidly spreading viral infection that has affected millions all over the world. With its rapid spread and increasing numbers, it becoming overwhelming for healthcare workers to diagnose condition contain from spreading. Hence become necessity automate diagnostic procedure. This will improve work efficiency as well keep safe getting exposed virus. Medical image analysis one rising research areas can tackle this issue with higher accuracy. paper conducts comparative study use recent deep learning models (VGG16, VGG19, DenseNet121, Inception-ResNet-V2, InceptionV3, Resnet50, Xception) deal detection classification coronavirus pneumonia cases. uses 7165 chest X-ray images (1536) (5629) patients. Confusion metrics performance were used analyze each model. Results show DenseNet121 (99.48% accuracy) showed better when compared other in study.

Language: Английский

---

A Self-Activated CNN Approach for Multi-Class Chest-Related COVID-19 Detection

Applied Sciences, Journal Year: 2021, Volume and Issue: 11(19), P. 9023 - 9023

Published: Sept. 28, 2021

Chest diseases can be dangerous and deadly. They include many chest infections such as pneumonia, asthma, edema, and, lately, COVID-19. COVID-19 has similar symptoms compared to breathing hardness burden. However, it is a challenging task differentiate from other diseases. Several related studies proposed computer-aided detection system for the single-class detection, which may misleading due of This paper proposes framework 15 types diseases, including disease, via X-ray modality. Two-way classification performed in Framework. First, deep learning-based convolutional neural network (CNN) architecture with soft-max classifier proposed. Second, transfer learning applied using fully-connected layer CNN that extracted features. The features are fed classical Machine Learning (ML) methods. improves accuracy increases predictability rates experimental results show framework, when state-of-the-art models diagnosing more robust, promising.

Language: Английский

---