A Quad-Step Approach to Uncertainty-Aware Deep Learning for Skin Cancer Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Asgharnezhad, Hamzeh, Tabarisaadi, Pegah, Khosravi, Abbas, Alizadehsani, Roohallah, Acharya, U. Rajendra
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911172779835392
author Asgharnezhad, Hamzeh
Tabarisaadi, Pegah
Khosravi, Abbas
Alizadehsani, Roohallah
Acharya, U. Rajendra
author_facet Asgharnezhad, Hamzeh
Tabarisaadi, Pegah
Khosravi, Abbas
Alizadehsani, Roohallah
Acharya, U. Rajendra
contents Accurate skin cancer diagnosis is vital for early treatment and improved patient outcomes. Deep learning (DL) models have shown promise in automating skin cancer classification, yet challenges remain due to data scarcity and limited uncertainty awareness. This study presents a comprehensive evaluation of DL-based skin lesion classification with transfer learning and uncertainty quantification (UQ) on the HAM10000 dataset. We benchmark several pre-trained feature extractors -- including CLIP variants, ResNet50, DenseNet121, VGG16, and EfficientNet-V2-Large -- combined with traditional classifiers such as SVM, XGBoost, and logistic regression. Multiple principal component analysis (PCA) settings (64, 128, 256, 512) are explored, with LAION CLIP ViT-H/14 and ViT-L/14 at PCA-256 achieving the strongest baseline results. In the UQ phase, Monte Carlo Dropout (MCD), Ensemble, and Ensemble Monte Carlo Dropout (EMCD) are applied and evaluated using uncertainty-aware metrics (UAcc, USen, USpe, UPre). Ensemble methods with PCA-256 provide the best balance between accuracy and reliability. Further improvements are obtained through feature fusion of top-performing extractors at PCA-256. Finally, we propose a feature-fusion based model trained with a predictive entropy (PE) loss function, which outperforms all prior configurations across both standard and uncertainty-aware evaluations, advancing trustworthy DL-based skin cancer diagnosis.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10302
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Quad-Step Approach to Uncertainty-Aware Deep Learning for Skin Cancer Classification
Asgharnezhad, Hamzeh
Tabarisaadi, Pegah
Khosravi, Abbas
Alizadehsani, Roohallah
Acharya, U. Rajendra
Computer Vision and Pattern Recognition
Artificial Intelligence
Accurate skin cancer diagnosis is vital for early treatment and improved patient outcomes. Deep learning (DL) models have shown promise in automating skin cancer classification, yet challenges remain due to data scarcity and limited uncertainty awareness. This study presents a comprehensive evaluation of DL-based skin lesion classification with transfer learning and uncertainty quantification (UQ) on the HAM10000 dataset. We benchmark several pre-trained feature extractors -- including CLIP variants, ResNet50, DenseNet121, VGG16, and EfficientNet-V2-Large -- combined with traditional classifiers such as SVM, XGBoost, and logistic regression. Multiple principal component analysis (PCA) settings (64, 128, 256, 512) are explored, with LAION CLIP ViT-H/14 and ViT-L/14 at PCA-256 achieving the strongest baseline results. In the UQ phase, Monte Carlo Dropout (MCD), Ensemble, and Ensemble Monte Carlo Dropout (EMCD) are applied and evaluated using uncertainty-aware metrics (UAcc, USen, USpe, UPre). Ensemble methods with PCA-256 provide the best balance between accuracy and reliability. Further improvements are obtained through feature fusion of top-performing extractors at PCA-256. Finally, we propose a feature-fusion based model trained with a predictive entropy (PE) loss function, which outperforms all prior configurations across both standard and uncertainty-aware evaluations, advancing trustworthy DL-based skin cancer diagnosis.
title A Quad-Step Approach to Uncertainty-Aware Deep Learning for Skin Cancer Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.10302