Malignant and non-malignant oral lesions classification and diagnosis with deep neural networks

Viduni Liyanage; Mengqiu Tao; Joon Soo Park; Kate N Wang; Somayyeh Azimi

doi:10.1016/j.jdent.2023.104657

Malignant and non-malignant oral lesions classification and diagnosis with deep neural networks

J Dent. 2023 Oct:137:104657. doi: 10.1016/j.jdent.2023.104657. Epub 2023 Aug 12.

Authors

Viduni Liyanage¹, Mengqiu Tao², Joon Soo Park³, Kate N Wang⁴, Somayyeh Azimi⁵

Affiliations

¹ International Research Collaborative - Oral Health and Equity, The University of Western Australia, Crawley, Western Australia, Australia; UWA Dental School, The University of Western Australia, Nedlands, Western Australia, Australia.
² School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, Australia.
³ International Research Collaborative - Oral Health and Equity, The University of Western Australia, Crawley, Western Australia, Australia; UWA Dental School, The University of Western Australia, Nedlands, Western Australia, Australia; School of Engineering, Information Technology and Physical Sciences, Federation University, Ballarat, Victoria, Australia. Electronic address: alex.park@uwa.edu.au.
⁴ School of Biomedical and Health Sciences, Royal Melbourne Institute of Technology, Bundoora, Victoria, Australia.
⁵ International Research Collaborative - Oral Health and Equity, The University of Western Australia, Crawley, Western Australia, Australia.

PMID: 37574105
DOI: 10.1016/j.jdent.2023.104657

Abstract

Objectives: Given the increasing incidence of oral cancer, it is essential to provide high-risk communities, especially in remote regions, with an affordable, user-friendly tool for visual lesion diagnosis. This proof-of-concept study explored the utility and feasibility of a smartphone application that can photograph and diagnose oral lesions.

Methods: The images of oral lesions with confirmed diagnoses were sourced from oral and maxillofacial textbooks. In total, 342 images were extracted, encompassing lesions from various regions of the oral cavity such as the gingiva, palate, and labial mucosa. The lesions were segregated into three categories: Class 1 represented non-neoplastic lesions, Class 2 included benign neoplasms, and Class 3 contained premalignant/malignant lesions. The images were analysed using MobileNetV3 and EfficientNetV2 models, with the process producing an accuracy curve, confusion matrix, and receiver operating characteristic (ROC) curve.

Results: The EfficientNetV2 model showed a steep increase in validation accuracy early in the iterations, plateauing at a score of 0.71. According to the confusion matrix, this model's testing accuracy for diagnosing non-neoplastic and premalignant/malignant lesions was 64% and 80% respectively. Conversely, the MobileNetV3 model exhibited a more gradual increase, reaching a plateau at a validation accuracy of 0.70. The MobileNetV3 model's testing accuracy for diagnosing non-neoplastic and premalignant/malignant lesions, according to the confusion matrix, was 64% and 82% respectively.

Conclusions: Our proof-of-concept study effectively demonstrated the potential accuracy of AI software in distinguishing malignant lesions. This could play a vital role in remote screenings for populations with limited access to dental practitioners. However, the discrepancies between the classification of images and the results of "non-malignant lesions" calls for further refinement of the models and the classification system used.

Clinical significance: The findings of this study indicate that AI software has the potential to aid in the identification or screening of malignant oral lesions. Further improvements are required to enhance accuracy in classifying non-malignant lesions.

Keywords: Artificial intelligence; Deep learning; Diagnosis; Machine learning; Oral Cancer.

MeSH terms

Dentists*
Humans
Neural Networks, Computer
Professional Role*
ROC Curve
Software