Multi-paradigm Vision Transformer ensemble with regional attention and MLP meta-fusion for explainable dermoscopic skin lesion classification
Frontiers in Medicine · 13.08.2026 · 13
DOI: 10.3389/fmed.2026.1864593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Medicine, online erschienen am 13.08.2026. Verfasst von Nemili Sravani und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, India. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
The automated classification of dermoscopic skin lesions is inherently challenging due to pronounced class imbalance, minimal inter-class variance, visual similarity across lesion types, and the requirement for clinically interpretable predictive outcomes.
Methods
The present study designed a heterogeneous Vision Transformer ensemble framework for seven-class skin lesion classification using the HAM10000 dataset. The framework integrates three architecturally distinct backbones Swin-Tiny, ViT-Base, and DeiT-Small enhanced with a novel Regional Attention Wrapper (RAW) for spatially selective feature aggregation. The generated outputs are combined via a stacking protocol wherein a trained MLP meta-learner resolves class-aware disagreements among the models. Class imbalance is addressed using class-adaptive augmentation with class-weighted focal loss and MixUp regularisation.
Results
The proposed framework achieved 98.37% accuracy, weighted F1-score of 98.39%, and mean AUC of 0.999, surpassing all three individual backbones across all metrics. MEL misclassifications were reduced by 78% compared to the weakest baseline, confirmed by McNemar's test ( p < 0.0001). Comprehensive ablation studies validate the contributions of the RAW module, each ensemble component, and each augmentation strategy. Three-fold cross-validation yields a mean accuracy of 96.14 ± 0.36% and bootstrap confidence interval analysis confirms the reliability and reproducibility of the reported results.
Discussion
An exhaustive explainability framework comprising Regional Attention Maps, GradCAM++, SHAP, and t-SNE provides complementary spatial, gradient-based, pixel-level, and embedding-level interpretability, ensuring clinical trust, transparency, and trustworthiness expected from an automated dermoscopy system.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, India.
Zitieren
APA
Sravani, N., & Koppu, S. (2026). Multi-paradigm Vision Transformer ensemble with regional attention and MLP meta-fusion for explainable dermoscopic skin lesion classification. Frontiers in Medicine, 13. https://doi.org/10.3389/fmed.2026.1864593
Vancouver
Sravani N, Koppu S. Multi-paradigm Vision Transformer ensemble with regional attention and MLP meta-fusion for explainable dermoscopic skin lesion classification. Frontiers in Medicine. 2026;13. doi:10.3389/fmed.2026.1864593
BibTeX
@article{Sravani2026,
author = {Sravani, Nemili and Koppu, Srinivas},
title = {Multi-paradigm Vision Transformer ensemble with regional attention and MLP meta-fusion for explainable dermoscopic skin lesion classification},
journal = {Frontiers in Medicine},
year = {2026},
volume = {13},
doi = {10.3389/fmed.2026.1864593}
}
EUVIMED