Bucket of deep transfer learning features and classification models for melanoma detection

TL;DR

This paper presents a transfer learning-based ensemble approach using deep convolutional neural network features for melanoma detection, demonstrating improved accuracy over existing methods.

Contribution

It introduces a novel ensemble classification framework utilizing pretrained deep CNN features for skin lesion melanoma prediction.

Findings

Effective melanoma detection with high accuracy

Outperforms state-of-the-art methods

Validates transfer learning and ensemble approach

Abstract

Malignant melanoma is the deadliest form of skin cancer and, in recent years, is rapidly growing in terms of the incidence worldwide rate. The most effective approach to targeted treatment is early diagnosis. Deep learning algorithms, specifically convolutional neural networks, represent a methodology for the image analysis and representation. They optimize the features design task, essential for an automatic approach on different types of images, including medical. In this paper, we adopted pretrained deep convolutional neural networks architectures for the image representation with purpose to predict skin lesion melanoma. Firstly, we applied a transfer learning approach to extract image features. Secondly, we adopted the transferred learning features inside an ensemble classification context. Specifically, the framework trains individual classifiers on balanced subspaces and combines the provided predictions through statistical measures. Experimental phase on datasets of skin lesion images is performed and results obtained show the effectiveness of the proposed approach with respect to state-of-the-art competitors.