Skin Cancer Classification Using Explainable Artificial Intelligence With an Ensemble Model and Rigorous Leakage Free Validation
- 1Mardin Artuklu University
Abstract
BackgroundReliable melanoma classification requires models that capture both local dermoscopic morphology and broader contextual patterns while maintaining auditable, leakageaware internal validation.
ObjectivesTo develop and internally validate an EfficientNetB0-Swin Transformer Tiny ensemble for classifying histopathologically verified dermoscopic images as benign melanocytic lesions or malignant melanoma.
MethodsThis retrospective diagnostic model-development and internal validation study screened 552,869 ISIC Archive records; filtering and dermatologist review yielded 1,199 uniquepatient and unique lesion images (578 benign and 621 malignant). Images were the predictors and histopathology was the reference. ImageNet pretrained EfficientNetB0 and Swin-T features were fused. Patient independent five fold validation used weighted sampling, mixup, label smoothing, AdamW, early stopping, and five view test time augmentation.
ResultsMean accuracy was 0.89325 {+/-} 0.03179, mean receiver operating characteristic area under the curve (ROC-AUC) was 0.96348 {+/-} 0.01695, and mean support weighted F1-score was 0.89300 {+/-} 0.03220. The fold level 95% confidence intervals were 0.8538-0.9327 for accuracy and 0.9424-0.9845 for ROC-AUC. Pooled counts were 526 true negatives, 52 false positives, 76 false negatives, and 545 true positives, yielding 87.76% sensitivity and 91.00% specificity. Qualitative Grad-CAM review showed peripheral artifact activation in two false positives and lesion centered activation in two correctly classified cases; these observations were not systematically scored.
LimitationsThe validation folds were also used for early stopping and checkpoint selection. Device stratified analysis, systematic interpretability scoring, calibration, and independent external validation were unavailable.
ConclusionsThe ensemble showed high internal discrimination and is intended only as a clinician facing adjunct. The error audit workflow enables targeted retrospective review, but external validation is required before clinical use or generalizability claims. The study was not registered.
Related
- An explainable artificial intelligence system for prognostic assessment and decision support in diabetic foot ulcer care: a multicentre derivation and validation study with prospective randomised evaluation
- An equal-weight soft-voting CNN ensemble with explainable AI for three-class knee radiograph classification
- An explainable artificial intelligence framework using electrocardiograms to predict mortality and major adverse cardiovascular events
- Generative Artificial Intelligence in Periodontology: Application of OpenAI Models for the Classification of Periodontitis and Risk Assessment in Patients Undergoing Supportive Periodontal Care
- Artificial Intelligence in Gastroenterology: Towards Explainable, Generalisable and Clinically Actionable Decision Support.
BibTeX
@misc{baran2026skin,
title = {{Skin Cancer Classification Using Explainable Artificial Intelligence With an Ensemble Model and Rigorous Leakage Free Validation}},
author = {M. T. BARAN and O. KARAKOYUN},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.02.26362011},
url = {https://www.medrxiv.org/content/10.64898/2026.09.02.26362011v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Skin Cancer Classification Using Explainable Artificial Intelligence With an Ensemble Model and Rigorous Leakage Free Validation
AU - M. T. BARAN
AU - O. KARAKOYUN
PY - 2026
DA - 2026/09/02
PB - medRxiv
DO - 10.64898/2026.09.02.26362011
UR - https://www.medrxiv.org/content/10.64898/2026.09.02.26362011v1
AB - BackgroundReliable melanoma classification requires models that capture both local dermoscopic morphology and broader contextual patterns while maintaining auditable, leakageaware internal validation. ObjectivesTo develop and internally validate an EfficientNetB0-Swin Transformer Tiny ensemble for classifying histopathologically verified dermoscopic images as benign melanocytic lesions or malignant melanoma. MethodsThis retrospective diagnostic model-development and internal validation study screened 552,869 ISIC Archive records; filtering and dermatologist review yielded 1,199 uniquepatient and unique lesion images (578 benign and 621 malignant). Images were the predictors and histopathology was the reference. ImageNet pretrained EfficientNetB0 and Swin-T features were fused. Patient independent five fold validation used weighted sampling, mixup, label smoothing, AdamW, early stopping, and five view test time augmentation. ResultsMean accuracy was 0.89325 {+/-} 0.03179, mean receiver operating characteristic area under the curve (ROC-AUC) was 0.96348 {+/-} 0.01695, and mean support weighted F1-score was 0.89300 {+/-} 0.03220. The fold level 95% confidence intervals were 0.8538-0.9327 for accuracy and 0.9424-0.9845 for ROC-AUC. Pooled counts were 526 true negatives, 52 false positives, 76 false negatives, and 545 true positives, yielding 87.76% sensitivity and 91.00% specificity. Qualitative Grad-CAM review showed peripheral artifact activation in two false positives and lesion centered activation in two correctly classified cases; these observations were not systematically scored. LimitationsThe validation folds were also used for early stopping and checkpoint selection. Device stratified analysis, systematic interpretability scoring, calibration, and independent external validation were unavailable. ConclusionsThe ensemble showed high internal discrimination and is intended only as a clinician facing adjunct. The error audit workflow enables targeted retrospective review, but external validation is required before clinical use or generalizability claims. The study was not registered.
ER -