TY - GEN
T1 - The Comparison of Deep Learning Model Efficiency for Classification of Oral White Lesions
AU - Phosri, Kunchidsong
AU - Treebupachatsakul, Treesukon
AU - Chomkwah, Wanwalee
AU - Tanpatanan, Tananan
AU - Thanathornwong, Bhornsawan
AU - Khovidhunkit, Siribang On Piboonniyom
AU - Poomrittigul, Suvit
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Oral cancer is one of the top health problems globally. Some white lesions of the oral cavity can develop into oral cancer if not screened and treated immediately. Modern screening technologies are popular for applying deep learning knowledge to screen and classify images. In this study, we used deep convolution neural network (CNN) to classify oral white lesions, ulcers, and normal anatomy using transfer learning, which can reduce training time. Ten pre-trained model of transfer learning including DenseNet121, DenseNet169, DenseNet201, Xception, ResNet50, InceptionResNetV2, InceptionV3, VGG16, VGG19, and EfficientNetB7 are implemented and evaluated. The evaluation of accuracy, precision, F1score, recall, sensitivity, confusion matrix, and AUC-ROC curve are discussed. The trained models of DenseNet169, DenseNet201, and Xception showed the highest testing accuracy of more than 90% and recall of 0.8833. In addition to the precision, F1score, and specificity, the DenseNet169 outperforms at 0.9034, 0.884, and 0.9417, respectively.
AB - Oral cancer is one of the top health problems globally. Some white lesions of the oral cavity can develop into oral cancer if not screened and treated immediately. Modern screening technologies are popular for applying deep learning knowledge to screen and classify images. In this study, we used deep convolution neural network (CNN) to classify oral white lesions, ulcers, and normal anatomy using transfer learning, which can reduce training time. Ten pre-trained model of transfer learning including DenseNet121, DenseNet169, DenseNet201, Xception, ResNet50, InceptionResNetV2, InceptionV3, VGG16, VGG19, and EfficientNetB7 are implemented and evaluated. The evaluation of accuracy, precision, F1score, recall, sensitivity, confusion matrix, and AUC-ROC curve are discussed. The trained models of DenseNet169, DenseNet201, and Xception showed the highest testing accuracy of more than 90% and recall of 0.8833. In addition to the precision, F1score, and specificity, the DenseNet169 outperforms at 0.9034, 0.884, and 0.9417, respectively.
KW - deep convolution neural network
KW - image classification
KW - oral white lesion
UR - http://www.scopus.com/inward/record.url?scp=85140629282&partnerID=8YFLogxK
U2 - 10.1109/ITC-CSCC55581.2022.9894916
DO - 10.1109/ITC-CSCC55581.2022.9894916
M3 - Conference contribution
AN - SCOPUS:85140629282
T3 - ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications
SP - 235
EP - 238
BT - ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022
Y2 - 5 July 2022 through 8 July 2022
ER -