MelanoFusion: An Explainable and Uncertainty-Aware Hybrid CNN–Transformer Framework for Dermoscopic Melanoma Detection

Melanoma is an aggressive skin cancer requiring early detection, yet automated analysis remains affected by lesion variation, calibration errors, uncertainty, and subgroup disparities. This study presents MelanoFusion, a hybrid framework integrating explainability, uncertainty estimation, and fairness-oriented representation learning for melanoma detection. It combines EfficientNetV2-S and Swin Transformer encoders with cross-attention, lesion attention, feature-pyramid processing, multi-scale transformer layers, and an uncertainty head. Images were resized to 224 × 224 and processed using hair removal, median filtering, contrast enhancement, colour normalization, and watershed-based lesion priors; U-Net was used for lesion segmentation. MelanoFusion was evaluated against DenseNet121, ResNet101, EfficientNetV2-S, ConvNeXt-Tiny, and Swin Transformer on HAM10000, ISIC 2018, and PH². Segmentation Dice was 0.878 on HAM10000 and 0.830 on PH². MelanoFusion achieved ROC-AUC values of 0.687, 0.740, and 0.844 on HAM10000, ISIC 2018, and PH², respectively. Calibration was favourable on HAM10000, with an expected calibration error of 0.116. Uncertainty was significantly associated with classification error, while subgroup analysis showed significant sensitivity differences across age groups but not sex. Ablation results indicated that several proposed components did not improve discrimination. The findings support joint evaluation of discrimination, calibration, uncertainty, explainability, and subgroup behaviour, while indicating the need for external validation and clinical evaluation before deployment.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-19
DOI
https://doi.org/10.21203/rs.3.rs-11208377/v1
Primary Topic
Cutaneous Melanoma Detection and Management
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

MelanoFusion: An Explainable and Uncertainty-Aware Hybrid CNN–Transformer Framework for Dermoscopic Melanoma Detection

Smita M Nirkhi, V. Purushothama Raju, Manish Motghare, Subhash R et al.
6 links
Research Square
Cutaneous Melanoma Detection and Management
preprint

MelanoFusion: An Explainable and Uncertainty-Aware Hybrid CNN–Transformer Framework for Dermoscopic Melanoma Detection

Smita M Nirkhi, V. Purushothama Raju, Manish Motghare, Subhash R, T. Bharath Kumar
preprint en

Abstract

Melanoma is an aggressive skin cancer requiring early detection, yet automated analysis remains affected by lesion variation, calibration errors, uncertainty, and subgroup disparities. This study presents MelanoFusion, a hybrid framework integrating explainability, uncertainty estimation, and fairness-oriented representation learning for melanoma detection. It combines EfficientNetV2-S and Swin Transformer encoders with cross-attention, lesion attention, feature-pyramid processing, multi-scale transformer layers, and an uncertainty head. Images were resized to 224 × 224 and processed using hair removal, median filtering, contrast enhancement, colour normalization, and watershed-based lesion priors; U-Net was used for lesion segmentation. MelanoFusion was evaluated against DenseNet121, ResNet101, EfficientNetV2-S, ConvNeXt-Tiny, and Swin Transformer on HAM10000, ISIC 2018, and PH². Segmentation Dice was 0.878 on HAM10000 and 0.830 on PH². MelanoFusion achieved ROC-AUC values of 0.687, 0.740, and 0.844 on HAM10000, ISIC 2018, and PH², respectively. Calibration was favourable on HAM10000, with an expected calibration error of 0.116. Uncertainty was significantly associated with classification error, while subgroup analysis showed significant sensitivity differences across age groups but not sex. Ablation results indicated that several proposed components did not improve discrimination. The findings support joint evaluation of discrimination, calibration, uncertainty, explainability, and subgroup behaviour, while indicating the need for external validation and clinical evaluation before deployment.

Research Square
Symbiosis International University (IN), ICFAI Foundation for Higher Education (IN)
Good health and well-being
Cutaneous Melanoma Detection and Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon