A Robust Hybrid Deep Convolutional Neural Network for COVID-19 Disease Identification from Chest X-ray Images

Sanida, Theodora; Tabakis, Irene-Maria; Sanida, Maria Vasiliki; Sideris, Argyrios; Dasygenis, Minas

doi:10.3390/info14060310

Cited by 8 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to [4], increasing recognition or classification accuracy requires a certain level of network depth. At [5], chest X-ray images are divided into three primary groups using a hybrid DCNN technique. DCNN hybrid network is created by the Inception module and VGG blocks together.…”

Section: Literature Reviewmentioning

confidence: 99%

Studying the Behavior of a Modified Deep Learning Model for Disease Detection Through X-ray Chest Images

Zanaj,

Balliu,

Basha

et al. 2024

ijacsa

View full text Add to dashboard Cite

In modern medical diagnostics, Deep Learning models are commonly used for illness diagnosis, especially over Xray chest images. Deep Learning approaches provide unmatched promise for early identification, prognosis, and treatment evaluation across a range of illnesses, by combining sophisticated algorithms with large datasets. It is crucial to research these models to lead to improved ones to progress toward disease identification's precision, effectiveness, and scalability. This paper presents the study of a CNN+VGG19 Deep Learning architecture (subsets of machine learning), both before and after its modification. The same dataset is used over the existing and modified models to compare metrics under the same conditions. They are compared using metrics like loss, accuracy, precision, sensitivity, and AUC. These metrics display lower values in the updated model than in the original one. The numbers demonstrate the occurrence of the overfitting phenomenon, which is most likely the result of the model's increased complexity for a small dataset. The noise in the images included in the dataset may also be the cause. As a result, it can be stated that regularization techniques should be applied; otherwise, layers of extraction and classification should not be added to the model to prevent overfitting.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Studying the Behavior of a Modified Deep Learning Model for Disease Detection Through X-ray Chest Images

Zanaj,

Balliu,

Basha

et al. 2024

ijacsa

View full text Add to dashboard Cite

show abstract

“…Sanida et al [31] proposed a DL model designed for a three-class categorization task, focusing on identifying pneumonia, normal lung conditions, and COVID-19 using chest X-ray images. This study examines the efficacy of the VGG19 model in its standard form and in modified forms that include the integration of inception blocks.…”

Section: Relative Workmentioning

confidence: 99%

An Advanced Deep Learning Framework for Multi-Class Diagnosis from Chest X-ray Images

Sanida,

Sideris

et al. 2024

Self Cite

View full text Add to dashboard Cite

Chest X-ray imaging plays a vital and indispensable role in the diagnosis of lungs, enabling healthcare professionals to swiftly and accurately identify lung abnormalities. Deep learning (DL) approaches have attained popularity in recent years and have shown promising results in automated medical image analysis, particularly in the field of chest radiology. This paper presents a novel DL framework specifically designed for the multi-class diagnosis of lung diseases, including fibrosis, opacity, tuberculosis, normal, viral pneumonia, and COVID-19 pneumonia, using chest X-ray images, aiming to address the need for efficient and accessible diagnostic tools. The framework employs a convolutional neural network (CNN) architecture with custom blocks to enhance the feature maps designed to learn discriminative features from chest X-ray images. The proposed DL framework is evaluated on a large-scale dataset, demonstrating superior performance in the multi-class diagnosis of the lung. In order to evaluate the effectiveness of the presented approach, thorough experiments are conducted against pre-existing state-of-the-art methods, revealing significant accuracy, sensitivity, and specificity improvements. The findings of the study showcased remarkable accuracy, achieving 98.88%. The performance metrics for precision, recall, F1-score, and Area Under the Curve (AUC) averaged 0.9870, 0.9904, 0.9887, and 0.9939 across the six-class categorization system. This research contributes to the field of medical imaging and provides a foundation for future advancements in DL-based diagnostic systems for lung diseases.

show abstract

“…The framework encompasses the benefits of IoMT sensors and extensive data analysis and prediction [20]. Sanida et al [21] proposed an approach that uses a robust hybrid deep convolutional neural network (DCNN) consisting of a combination of VGG blocks (visual geometry group) and an inception module for prompt and accurate identification [21]. In a recent study by Dubey et al [22], ensemble deep learning (EDL) was superior to deep transfer learning (TL) in both non-augmented and augmented frameworks for the classification of COVID-19 patients based on hybrid deep-learning-based lung segmentation.…”

Section: Descriptive Analysismentioning

confidence: 99%

Emerging Technology-Driven Hybrid Models for Preventing and Monitoring Infectious Diseases: A Comprehensive Review and Conceptual Framework

Albahlal

2023

Diagnostics

View full text Add to dashboard Cite

The emergence of the infectious diseases, such as the novel coronavirus, as a significant global health threat has emphasized the urgent need for effective treatments and vaccines. As infectious diseases become more common around the world, it is important to have strategies in place to prevent and monitor them. This study reviews hybrid models that incorporate emerging technologies for preventing and monitoring infectious diseases. It also presents a comprehensive review of the hybrid models employed for preventing and monitoring infectious diseases since the outbreak of COVID-19. The review encompasses models that integrate emerging and innovative technologies, such as blockchain, Internet of Things (IoT), big data, and artificial intelligence (AI). By harnessing these technologies, the hybrid system enables secure contact tracing and source isolation. Based on the review, a hybrid conceptual framework model proposes a hybrid model that incorporates emerging technologies. The proposed hybrid model enables effective contact tracing, secure source isolation using blockchain technology, IoT sensors, and big data collection. A hybrid model that incorporates emerging technologies is proposed as a comprehensive approach to preventing and monitoring infectious diseases. With continued research on and the development of the proposed model, the global efforts to effectively combat infectious diseases and safeguard public health will continue.

show abstract

A Robust Hybrid Deep Convolutional Neural Network for COVID-19 Disease Identification from Chest X-ray Images

Cited by 8 publications

References 36 publications

Studying the Behavior of a Modified Deep Learning Model for Disease Detection Through X-ray Chest Images

Studying the Behavior of a Modified Deep Learning Model for Disease Detection Through X-ray Chest Images

An Advanced Deep Learning Framework for Multi-Class Diagnosis from Chest X-ray Images

Emerging Technology-Driven Hybrid Models for Preventing and Monitoring Infectious Diseases: A Comprehensive Review and Conceptual Framework

Contact Info

Product

Resources

About