# Deep Learning-Based Automated Detection of Oral Leukoplakia in Clinical Imaging

## TL;DR

This paper presents a deep learning system that can accurately detect oral leukoplakia in clinical images, potentially aiding early diagnosis of oral cancer.

## Contribution

A novel deep learning model using EfficientNetB0 with high accuracy and interpretability for detecting oral leukoplakia in clinical settings.

## Key findings

- The EfficientNetB0 model achieved 97.54% accuracy with an AUC of 0.993 in detecting oral leukoplakia.
- Class Activation Mapping localized lesions effectively, aligning with clinical diagnostic criteria.
- The model performed robustly under varying illumination and oral cavity locations.

## Abstract

Objective: This study aims to develop and validate a deep learning-based system for automated identification of oral leukoplakia (OLK), addressing diagnostic challenges in clinical practice.

Methods: We conducted a comparative analysis of 19 convolutional neural network (CNN) architectures using 446 clinical images of histopathologically confirmed oral leukoplakia cases. The dataset was augmented with 1,041 normal oral mucosa images for comparison. A fine-tuned EfficientNetB0 architecture was selected as the optimal model. Class Activation Mapping (CAM) visualized decision-making regions, with performance evaluated through area under the receiver operating characteristic curve (AUC-ROC) analysis and accuracy metrics.

Results: The EfficientNetB0 model achieved 97.54% accuracy (95% confidence interval (CI): 95.2%-99.1%) with an AUC of 0.993 (95% CI: 0.981-0.998). Activation mapping demonstrated precise localization of leukoplakic lesions, correlating with clinical diagnostic criteria. The model maintained robust performance across varying illumination conditions and oral cavity locations.

Conclusion: This deep learning system demonstrates expert-level diagnostic capability for oral leukoplakia identification, showing potential for integration into clinical decision support systems. The model's high diagnostic accuracy and interpretability through activation mapping address critical needs in early oral cancer detection and screening programs.