TY - GEN
T1 - Comparison of CNN- and Transformer-based Architectures for Automated Oral Epithelium Segmentation on Whole Slide Images
AU - Srisermphoak, Napat
AU - Amornphimoltham, Panomwat
AU - Chaisuparat, Risa
AU - Achararit, Paniti
AU - Fuangrod, Todsaporn
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Oral cancer is one of the most commonly found cancers worldwide. Oral Epithelial Dysplasia (OED) is an Oral Potentially Malignant Disorder (OPMD) that can be characterized for preventive oral cancer screening. The standard for OED histological grading is conducted via the epithelial regions of tissue biopsies. However, this procedure is laborious, time-consuming, and subjective; consequently, it is prone to variability due to fatigue and limited expertise. Therefore, this study aims to explore the potential of using Convolutional Neural Network (CNN) and Transformer models for an automated epithelium segmentation algorithm directly from Whole Slide Images (WSIs). This approach can reduce the manual process and support pathologists in grading activities. Accordingly, candidate architectures based on CNN and Transformer are selected: UNet, ResNet50-UNet, VGG19-UNet, Swin-UNet, and MISSFormer. These models are trained using patch-based segmentation to mitigate the high computational cost caused by processing WSIs. The results indicate that UNet, optimized with the ADAM optimizer, demonstrates the best performance in patch-based segmentation with Intersection over Union (IoU) of 0.82 and Dice-Similarity Coefficient (DSC) of 0.87. Furthermore, this model achieves the highest IoU and DSC for tissue-level prediction, scoring 0.88 and 0.94, respectively. According to the experiment, overlapping and non-overlapping patching strategies perform similarly in most of the selected architectures. The latter approach, hence, is suggested for computational efficiency. These results can support enhancing automated epithelium segmentation to provide a reliable tool for assisting pathologists.
AB - Oral cancer is one of the most commonly found cancers worldwide. Oral Epithelial Dysplasia (OED) is an Oral Potentially Malignant Disorder (OPMD) that can be characterized for preventive oral cancer screening. The standard for OED histological grading is conducted via the epithelial regions of tissue biopsies. However, this procedure is laborious, time-consuming, and subjective; consequently, it is prone to variability due to fatigue and limited expertise. Therefore, this study aims to explore the potential of using Convolutional Neural Network (CNN) and Transformer models for an automated epithelium segmentation algorithm directly from Whole Slide Images (WSIs). This approach can reduce the manual process and support pathologists in grading activities. Accordingly, candidate architectures based on CNN and Transformer are selected: UNet, ResNet50-UNet, VGG19-UNet, Swin-UNet, and MISSFormer. These models are trained using patch-based segmentation to mitigate the high computational cost caused by processing WSIs. The results indicate that UNet, optimized with the ADAM optimizer, demonstrates the best performance in patch-based segmentation with Intersection over Union (IoU) of 0.82 and Dice-Similarity Coefficient (DSC) of 0.87. Furthermore, this model achieves the highest IoU and DSC for tissue-level prediction, scoring 0.88 and 0.94, respectively. According to the experiment, overlapping and non-overlapping patching strategies perform similarly in most of the selected architectures. The latter approach, hence, is suggested for computational efficiency. These results can support enhancing automated epithelium segmentation to provide a reliable tool for assisting pathologists.
KW - Artificial Intelligence
KW - Convolutional Neuron Networks
KW - Digital Pathology
KW - Epithelium Segmentation
KW - Vision Transformer
KW - Whole Slide Images
UR - http://www.scopus.com/inward/record.url?scp=85179558062&partnerID=8YFLogxK
U2 - 10.1109/BMEiCON60347.2023.10322006
DO - 10.1109/BMEiCON60347.2023.10322006
M3 - Conference contribution
AN - SCOPUS:85179558062
T3 - BMEiCON 2023 - 15th Biomedical Engineering International Conference
BT - BMEiCON 2023 - 15th Biomedical Engineering International Conference
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th Biomedical Engineering International Conference, BMEiCON 2023
Y2 - 28 October 2023 through 31 October 2023
ER -