Classification of Oral Cancer and Leukoplakia Using Oral Images and Deep Learning with Multi-Scale Random Crop Self-Training

Itsuki Hamada, Takaaki Ohkawauchi, Chisa Shibayama, Kitaro Yoshimitsu, Nobuyuki Kaibuchi, Katsuhisa Sakaguchi, Toshihiro Okamoto, Jun Ohya

2025

Abstract

This paper proposes Multi-Scale Random Crop Self-Training (MSRCST) for classifying oral cancers and leukoplakia using oral images acquired by our dermoscope. MSRCST comprises the following three key modules: (1) Multi-Scale Random Crop, which extracts image patches at various scales from high-resolution images, preserving both local details and global contextual information essential for accurate classification, (2) Selection based on Confidence, which employs a teacher model to assign confidence scores to each cropped patch, selecting only those with high confidence for further training and ensuring the model focusing on diagnostically relevant features, (3) Iteration of Self-training, which iteratively retrains the model using the selected high-confidence, pseudo-labeled data, progressively enhancing accuracy. In our experiments, we applied MSRCST to classify images of oral cancer and leukoplakia. When combined with MixUp data augmentation, MSRCST achieved an average classification accuracy of 71.71%, outperforming traditional resizing and random cropping methods. Additionally, it effectively reduced misclassification rates, as demonstrated by improved confusion matrices, thereby enhancing diagnostic reliability.

Paper Citation

in Harvard Style

Hamada I., Ohkawauchi T., Shibayama C., Yoshimitsu K., Kaibuchi N., Sakaguchi K., Okamoto T. and Ohya J. (2025). Classification of Oral Cancer and Leukoplakia Using Oral Images and Deep Learning with Multi-Scale Random Crop Self-Training. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 780-787. DOI: 10.5220/0013296500003905

in Bibtex Style

@conference{icpram25,
author={Itsuki Hamada and Takaaki Ohkawauchi and Chisa Shibayama and Kitaro Yoshimitsu and Nobuyuki Kaibuchi and Katsuhisa Sakaguchi and Toshihiro Okamoto and Jun Ohya},
title={Classification of Oral Cancer and Leukoplakia Using Oral Images and Deep Learning with Multi-Scale Random Crop Self-Training},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={780-787},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013296500003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Classification of Oral Cancer and Leukoplakia Using Oral Images and Deep Learning with Multi-Scale Random Crop Self-Training
SN - 978-989-758-730-6
AU - Hamada I.
AU - Ohkawauchi T.
AU - Shibayama C.
AU - Yoshimitsu K.
AU - Kaibuchi N.
AU - Sakaguchi K.
AU - Okamoto T.
AU - Ohya J.
PY - 2025
SP - 780
EP - 787
DO - 10.5220/0013296500003905
PB - SciTePress