Back

A Hybrid Deep Learning Ensemble for Accurate Skin Cancer Classification

Rahi, A.

2025-09-09 radiology and imaging
10.1101/2025.09.03.25335044 medRxiv
Show abstract

Skin cancer is one of the most common types of cancer worldwide, and early detection is crucial for improving patient survival rates. In this study, we propose a hybrid deep learning ensemble model for the automatic classification of dermoscopic images into benign and malignant categories. The framework integrates multiple deep learning architectures and combines their predictive strengths through a meta-learning approach. Experimental evaluations on a benchmark dataset demonstrated that the proposed ensemble achieved a classification accuracy of 91.7% and a ROC-AUC score of 0.974, outperforming individual models. These results highlight the potential of hybrid ensemble methods as reliable computer- aided diagnostic tools for dermatology, contributing to early and accurate skin cancer detection.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.