Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images
Introduction: In humanity’s ongoing fight against its common enemy of COVID-19, researchers have been relentless in finding efficient technologies to support mitigation, diagnosis, management, contact tracing, and ultimately vaccination. Objectives: Engineers and computer scientists have deployed th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | Journal of King Saud University: Science |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1018364722000799 |
| _version_ | 1828858599204454400 |
|---|---|
| author | Mohamed Hammad Lo'ai Tawalbeh Abdullah M. Iliyasu Ahmed Sedik Fathi E. Abd El-Samie Monagi H. Alkinani Ahmed A. Abd El-Latif |
| author_facet | Mohamed Hammad Lo'ai Tawalbeh Abdullah M. Iliyasu Ahmed Sedik Fathi E. Abd El-Samie Monagi H. Alkinani Ahmed A. Abd El-Latif |
| author_sort | Mohamed Hammad |
| collection | DOAJ |
| description | Introduction: In humanity’s ongoing fight against its common enemy of COVID-19, researchers have been relentless in finding efficient technologies to support mitigation, diagnosis, management, contact tracing, and ultimately vaccination. Objectives: Engineers and computer scientists have deployed the potent properties of deep learning models (DLMs) in COVID-19 detection and diagnosis. However, publicly available datasets are often adulterated during collation, transmission, or storage. Meanwhile, inadequate, and corrupted data are known to impact the learnability and efficiency of DLMs. Methods: This study focuses on enhancing previous efforts via two multimodal diagnostic systems to extract required features for COVID-19 detection using adulterated chest X-ray images. Our proposed DLM consists of a hierarchy of convolutional and pooling layers that are combined to support efficient COVID-19 detection using chest X-ray images. Additionally, a batch normalization layer is used to curtail overfitting that usually arises from the convolution and pooling (CP) layers. Results: In addition to matching the performance of standard techniques reported in the literature, our proposed diagnostic systems attain an average accuracy of 98% in the detection of normal, COVID-19, and viral pneumonia cases using corrupted and noisy images. Conclusions: Such robustness is crucial for real-world applications where data is usually unavailable, corrupted, or adulterated. |
| first_indexed | 2024-12-13T01:59:49Z |
| format | Article |
| id | doaj.art-4e8cb90fc0994f618ea48ff2b7646625 |
| institution | Directory Open Access Journal |
| issn | 1018-3647 |
| language | English |
| last_indexed | 2024-12-13T01:59:49Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Science |
| spelling | doaj.art-4e8cb90fc0994f618ea48ff2b76466252022-12-22T00:03:17ZengElsevierJournal of King Saud University: Science1018-36472022-04-01343101898Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted imagesMohamed Hammad0Lo'ai Tawalbeh1Abdullah M. Iliyasu2Ahmed Sedik3Fathi E. Abd El-Samie4Monagi H. Alkinani5Ahmed A. Abd El-Latif6Information Technology Department, Faculty of Computers and Information, Menoufia University, Shebin El-koom 32511, EgyptDirector of Cyber Security Center, Department of Computing and Cybersecurity, Texas A&M University-San Antonio, San Antonio, TX, USASchool of Computing, Tokyo Institute of Technology, Yokohama 226-8502, JapanDepartment of the Robotics and Intelligent Machines, Kafrelsheikh University, Kafrelsheikh 33511, EgyptDepartment of Electronics and Electrical Communications Menoufa University, Menouf 32952, EgyptCollege of Computer Sciences and Engineering, Department of Computer Science and Artificial Intelligence, University of Jeddah, Saudi ArabiaEIAS Data Science Lab, College of Computer and Information Sciences, Prince Sultan University, Riyadh 11586, Saudi Arabia; Department of Mathematics and Computer Science, Faculty of Science, Menoufia University, Shebin El-koom 32511, Egypt; Corresponding author at: Department of Computing and Cyber Security, Texas A&M University-San Antonio, One University Way, San Antonio, TX 78224, USA..Introduction: In humanity’s ongoing fight against its common enemy of COVID-19, researchers have been relentless in finding efficient technologies to support mitigation, diagnosis, management, contact tracing, and ultimately vaccination. Objectives: Engineers and computer scientists have deployed the potent properties of deep learning models (DLMs) in COVID-19 detection and diagnosis. However, publicly available datasets are often adulterated during collation, transmission, or storage. Meanwhile, inadequate, and corrupted data are known to impact the learnability and efficiency of DLMs. Methods: This study focuses on enhancing previous efforts via two multimodal diagnostic systems to extract required features for COVID-19 detection using adulterated chest X-ray images. Our proposed DLM consists of a hierarchy of convolutional and pooling layers that are combined to support efficient COVID-19 detection using chest X-ray images. Additionally, a batch normalization layer is used to curtail overfitting that usually arises from the convolution and pooling (CP) layers. Results: In addition to matching the performance of standard techniques reported in the literature, our proposed diagnostic systems attain an average accuracy of 98% in the detection of normal, COVID-19, and viral pneumonia cases using corrupted and noisy images. Conclusions: Such robustness is crucial for real-world applications where data is usually unavailable, corrupted, or adulterated.http://www.sciencedirect.com/science/article/pii/S1018364722000799Artificial intelligenceDeep learningCOVID-19Corona virusChest X-rayImage processing |
| spellingShingle | Mohamed Hammad Lo'ai Tawalbeh Abdullah M. Iliyasu Ahmed Sedik Fathi E. Abd El-Samie Monagi H. Alkinani Ahmed A. Abd El-Latif Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images Journal of King Saud University: Science Artificial intelligence Deep learning COVID-19 Corona virus Chest X-ray Image processing |
| title | Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images |
| title_full | Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images |
| title_fullStr | Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images |
| title_full_unstemmed | Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images |
| title_short | Efficient multimodal deep-learning-based COVID-19 diagnostic system for noisy and corrupted images |
| title_sort | efficient multimodal deep learning based covid 19 diagnostic system for noisy and corrupted images |
| topic | Artificial intelligence Deep learning COVID-19 Corona virus Chest X-ray Image processing |
| url | http://www.sciencedirect.com/science/article/pii/S1018364722000799 |
| work_keys_str_mv | AT mohamedhammad efficientmultimodaldeeplearningbasedcovid19diagnosticsystemfornoisyandcorruptedimages AT loaitawalbeh efficientmultimodaldeeplearningbasedcovid19diagnosticsystemfornoisyandcorruptedimages AT abdullahmiliyasu efficientmultimodaldeeplearningbasedcovid19diagnosticsystemfornoisyandcorruptedimages AT ahmedsedik efficientmultimodaldeeplearningbasedcovid19diagnosticsystemfornoisyandcorruptedimages AT fathieabdelsamie efficientmultimodaldeeplearningbasedcovid19diagnosticsystemfornoisyandcorruptedimages AT monagihalkinani efficientmultimodaldeeplearningbasedcovid19diagnosticsystemfornoisyandcorruptedimages AT ahmedaabdellatif efficientmultimodaldeeplearningbasedcovid19diagnosticsystemfornoisyandcorruptedimages |