Skin lesion detection based on an ensemble of deep convolutional neural network

TL;DR

This paper introduces an ensemble of deep convolutional neural networks that combines multiple models' outputs to improve the accuracy of classifying dermoscopy images for skin lesion detection, addressing a critical health issue.

Contribution

It presents a novel fusion approach that combines four neural networks' outputs weighted by confidence to enhance skin lesion classification accuracy.

Findings

Fusion approach outperforms individual neural networks

Weighted confidence improves ensemble accuracy

Effective for skin lesion classification

Abstract

Skin cancer is a major public health problem, with over 5 million newly diagnosed cases in the United States each year. Melanoma is the deadliest form of skin cancer, responsible for over 9,000 deaths each year. In this paper, we propose an ensemble of deep convolutional neural networks to classify dermoscopy images into three classes. To achieve the highest classification accuracy, we fuse the outputs of the softmax layers of four different neural architectures. For aggregation, we consider the individual accuracies of the networks weighted by the confidence values provided by their final softmax layers. This fusion-based approach outperformed all the individual neural networks regarding classification accuracy.