TY - GEN
T1 - COVID-19 Identification and Analysis with CT Scan Images using DenseNet and Support Vector Machine
AU - Lim, Yu Jie
AU - Lim, Kian Ming
AU - Lee, Chin Poo
AU - Chang, Roy Kwang Yang
AU - Lim, Jit Yan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Medical image analysis is the process of analyzing and interpreting medical images to diagnose diseases, assess disease progression, surgical planning and guide medical treatments by extracting clinically useful information from medical images. Medical image analysis serves an important role in applications in healthcare. With the advancement of deep learning techniques, the utilization of artificial intelligence for medical image analysis has experienced a notable surge, leading to improved accuracy and efficiency in diagnoses and treatment planning. In the present work, a pre-trained transfer learning model, DenseNet201 as a feature extractor, with a classifier of Support Vector Machine (SVM) is aimed to address the classification challenge associated with COVID-19 chest CT images. The evaluation of the proposed DenseNet201-SVM model has been conducted on three benchmark datasets: SARS-CoV-2 CT images, COVID-CT and Integrative CT images and CFs for COVID-19 (iCTCF) datasets and achieved accuracy of 98.99%, 93.33% and 99.25% respectively. The total number of images for each dataset are 2482, 746 and 19685. There are only two classes in first and second datasets, whereas the third dataset has three classes. The result is compared with other existing methods and the proposed DenseNet201-SVM model has outperformed other methods.
AB - Medical image analysis is the process of analyzing and interpreting medical images to diagnose diseases, assess disease progression, surgical planning and guide medical treatments by extracting clinically useful information from medical images. Medical image analysis serves an important role in applications in healthcare. With the advancement of deep learning techniques, the utilization of artificial intelligence for medical image analysis has experienced a notable surge, leading to improved accuracy and efficiency in diagnoses and treatment planning. In the present work, a pre-trained transfer learning model, DenseNet201 as a feature extractor, with a classifier of Support Vector Machine (SVM) is aimed to address the classification challenge associated with COVID-19 chest CT images. The evaluation of the proposed DenseNet201-SVM model has been conducted on three benchmark datasets: SARS-CoV-2 CT images, COVID-CT and Integrative CT images and CFs for COVID-19 (iCTCF) datasets and achieved accuracy of 98.99%, 93.33% and 99.25% respectively. The total number of images for each dataset are 2482, 746 and 19685. There are only two classes in first and second datasets, whereas the third dataset has three classes. The result is compared with other existing methods and the proposed DenseNet201-SVM model has outperformed other methods.
KW - COVID-19
KW - CT-Scan
KW - DenseNet
KW - Medical Image Analysis
KW - Support Vector Machine
UR - http://www.scopus.com/inward/record.url?scp=85174414836&partnerID=8YFLogxK
U2 - 10.1109/ICoICT58202.2023.10262543
DO - 10.1109/ICoICT58202.2023.10262543
M3 - Conference Proceeding
AN - SCOPUS:85174414836
T3 - 2023 11th International Conference on Information and Communication Technology, ICoICT 2023
SP - 254
EP - 259
BT - 2023 11th International Conference on Information and Communication Technology, ICoICT 2023
T2 - 11th International Conference on Information and Communication Technology, ICoICT 2023
Y2 - 23 August 2023 through 24 August 2023
ER -