Calibration-Aware Heterogeneous Multimodal Ensemble for Multi-Class Skin Lesion Diagnosis
Diagnostics · 01.11.2026 · 16 (21) · 3613
DOI: 10.3390/diagnostics16213613 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 01.11.2026. Verfasst von Ozan Alptekin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Natural and Applied Sciences, Dokuz Eylul University, 35390 İzmir, Türkiye. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Reliable classification of skin lesions is essential for early melanoma detection; however, substantial visual overlap among lesion types and pronounced class imbalance continue to limit the performance and reliability of existing automated systems. These challenges motivate the integration of complementary visual representations with clinical metadata to improve discrimination across lesion classes.
Methods
This study introduces a calibrated multimodal ensemble learning framework for skin lesion classification. The proposed framework combines visual features extracted from Swin Transformer, EVA-02, and CoAtNet architectures with patient age and anatomical region information. A two-stage adaptive temperature scaling is applied to calibrate the predicted probabilities of the ensemble.
Results
Experimental evaluation on the International Skin Imaging Collaboration (ISIC 2019) dataset demonstrates strong classification performance, achieving a macro-F1 score of 0.91 and a macro-AUC of 0.99. The framework further showed robust generalization on the official ISIC 2019 benchmark set, attaining a balanced accuracy of 0.65. The external validation on the PH2 dataset yielded a macro-F1 score of 0.93 and an ROC-AUC of 0.96.
Conclusions
These findings demonstrate that combining heterogeneous visual representations, clinical metadata, and calibration-aware ensemble learning provides a robust and trustworthy solution for skin lesion classification and computer-aided dermatological diagnosis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Natural and Applied Sciences, Dokuz Eylul University, 35390 İzmir, Türkiye.
- Department of Computer Engineering, Dokuz Eylul University, 35390 İzmir, Türkiye.
- Bioinformatics Group, Department of Computer Science, Vrije Universiteit Amsterdam, 1081 HV Amsterdam, The Netherlands.
ORCID-Profile: Ozan Alptekin, Feristah Dalkilic, Zerrin Isik
Zitieren
APA
Alptekin, O., Dalkilic, F., & Isik, Z. (2026). Calibration-Aware Heterogeneous Multimodal Ensemble for Multi-Class Skin Lesion Diagnosis. Diagnostics, 16(21), 3613. https://doi.org/10.3390/diagnostics16213613
Vancouver
Alptekin O, Dalkilic F, Isik Z. Calibration-Aware Heterogeneous Multimodal Ensemble for Multi-Class Skin Lesion Diagnosis. Diagnostics. 2026;16(21):3613. doi:10.3390/diagnostics16213613
BibTeX
@article{Alptekin2026,
author = {Alptekin, Ozan and Dalkilic, Feristah and Isik, Zerrin},
title = {Calibration-Aware Heterogeneous Multimodal Ensemble for Multi-Class Skin Lesion Diagnosis},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {21},
pages = {3613},
doi = {10.3390/diagnostics16213613}
}
EUVIMED