Deep Learning-Based Multiclass Classification of Oral Lesions with Stratified Augmentation

2025-11-26

AI Summary

Oral cancer diagnosis is frequently delayed due to visual similarity between benign and malignant lesions, necessitating early and accurate computer-aided identification. To address this, we propose a deep learning-based multi-class classification framework for sixteen oral lesion categories. Our method innovatively integrates hierarchical data partitioning, image-level adaptive augmentation, and synthetic oversampling to effectively mitigate severe class imbalance. The model employs an enhanced deep convolutional neural network architecture and leverages hierarchical cross-validation to improve generalizability. Evaluated on a real-world clinical dataset, the framework achieves 83.33% accuracy, 89.12% precision, and 77.31% recall. Notably, performance on underrepresented classes improves substantially. Comparative experiments demonstrate consistent superiority over state-of-the-art methods. This work provides a robust, reliable, and clinically applicable technical foundation for early auxiliary diagnosis of oral cancer.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Distributed Search

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Oral cancer is highly common across the globe and is mostly diagnosed during the later stages due to the close visual similarity to benign, precancerous, and malignant lesions in the oral cavity. Implementing computer aided diagnosis systems early on has the potential to greatly improve clinical outcomes. This research intends to use deep learning to build a multiclass classifier for sixteen different oral lesions. To overcome the challenges of limited and imbalanced datasets, the proposed technique combines stratified data splitting and advanced data augmentation and oversampling to perform the classification. The experimental results, which achieved 83.33 percent accuracy, 89.12 percent precision, and 77.31 percent recall, demonstrate the superiority of the suggested model over state of the art methods now in use. The suggested model effectively conveys the effectiveness of oversampling and augmentation strategies in situations where the minority class classification performance is noteworthy. As a first step toward trustworthy computer aided diagnostic systems for the early detection of oral cancer in clinical settings, the suggested framework shows promise.

Problem

• Classifying 16 types of oral lesions using deep learning
• Addressing data imbalance with stratified augmentation techniques
• Improving early oral cancer detection via computer-aided diagnosis

Innovation

• Deep learning multiclass classifier for oral lesions
• Stratified data splitting with advanced augmentation
• Oversampling to improve minority class performance