Enhancing deep learning classification performance of tongue lesions in imbalanced data: mosaic-based soft labeling with curriculum learning.

Journal: BMC oral health
Published Date:

Abstract

BACKGROUND: Oral potentially malignant disorders (OPMDs) are associated with an increased risk of cancer of the oral cavity including the tongue. The early detection of oral cavity cancers and OPMDs is critical for reducing cancer-specific morbidity and mortality. Recently, there have been studies to apply the rapidly advancing technology of deep learning for diagnosing oral cavity cancer and OPMDs. However, several challenging issues such as class imbalance must be resolved to effectively train a deep learning model for medical imaging classification tasks. The aim of this study is to evaluate a new technique of artificial intelligence to improve the classification performance in an imbalanced tongue lesion dataset.

Authors

  • Sung-Jae Lee
    From the Department of Psychiatry & Biobehavioral Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA.
  • Hyun Jun Oh
    Oral Oncology Clinic, National Cancer Center, Goyang, Republic of Korea.
  • Young-Don Son
    Department of Biomedical Engineering, Gachon University, Inchon, Republic of Korea.
  • Jong-Hoon Kim
    Department of Psychiatry, Gil Medical Center, Gachon University College of Medicine, Gachon University, Incheon, Republic of Korea.
  • Ik-Jae Kwon
    Department of Oral and Maxillofacial Surgery, Seoul National University Dental Hospital, Seoul, Republic of Korea.
  • Bongju Kim
    Dental Life Science Research Institute, Seoul National University Dental Hospital, Seoul, Republic of Korea.
  • Jong-Ho Lee
    Ministry of Science and ICT, Sejong, Republic of Korea.
  • Hang-Keun Kim
    Department of Biomedical Engineering, Gachon University, Inchon, Republic of Korea.