This study investigates whether class imbalance can be mitigated through random under-sampling, random over-sampling, and medically informed image augmentation when training three representative deep learning architectures: EfficientNet, Vision Transformer, and Swin Transformer.
Abstract
Simple Summary Early detection of oral cancer is essential for improving patient survival, yet artificial intelligence models often struggle because available clinical image datasets are small and highly imbalanced, with relatively few malignant cases. This study investigates whether class imbalance can be mitigated through random under-sampling, random over-sampling, and medically informed image augmentation when training three representative deep learning architectures: EfficientNet, Vision Transformer, and Swin Transformer. Using a publicly available dataset of oral cavity photographs and a unified five-fold cross-validation framework, we compared these strategies using both multiclass classification and a clinically oriented malignant-risk evaluation. The results indicate that data augmentation generally improves minority-class detection while maintaining competitive overall classification performance. Nevertheless, external multicenter validation and prospective clinical studies are required before routine clinical application.
A review of transformer-based architectures applied to lung cancer detection and classification highlights potential future directions, including model optimization, data standardization, and validation across diverse clinical environments, to enhance the reliability and integration of transformer-based models in healt...
Neha Thakur, Pradeep Chouksey, P. Sadotra et al.· Discover Artificial Intellig...· 0 citations
These findings demonstrate that reliable medical AI systems require systematic optimization of preprocessing techniques, model architecture, data augmentation strategies, and clinically meaningful evaluation metrics rather than maximizing a single performance indicator.
YongJun Kim, Ji-Yeoun Lee· BioMedInformatics· 0 citations
A comprehensive deep learning-based framework that leverages three benchmark datasets—PH2, ISIC (Benign vs Malignant), and HAM10000—using transfer learning and ensemble techniques is presented, demonstrating a notable increase in classification accuracy.
A. D. Hayder, J. Saeed· passer of basic and applied...· 0 citations
STLC-Net (Skin Transfer Learning Classification Network) is introduced, a robust, zero-data-leakage framework for automated seven-class skin lesion classification using the benchmark HAM10000 dataset and integrated into an interactive web deployment for real-time, interpretable clinical decision support.
Breast cancer remains the most frequently diagnosed malignancy and a leading cause of cancer death among women worldwide, with GLOBOCAN 2022 estimating 2.30 million new cases and 666,103 deaths globally (Bray et al., 2024; Gu et al., 2026). Artificial intelligence (AI), and deep learning (DL) in particular, has become...
Nitish Verma, Ayushmaan Sharma, Kelvin Luntsi et al.· International Journal For Mu...· 0 citations
Quantitative evaluation using TMAI and complementary XAI methods provides additional evidence that the model's predictions are grounded in clinically relevant lesion regions rather than background artefacts, supporting the potential of the framework for accurate and interpretable automated skin lesion classification.
NE. Sravani, Srinivas Koppu· Frontiers in Public Health· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.