Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble

TL;DR

This paper presents a deep neural network ensemble approach for classifying melanoma, nevus, and seborrheic keratosis, achieving high accuracy in the ISBI Challenge 2017 with an AUC of up to 0.993.

Contribution

It introduces an ensemble method for skin lesion classification and reports competitive evaluation results on a standardized challenge dataset.

Findings

Validation score of 0.958 achieved

Melanoma classifier AUC of 0.924

Seborrheic keratosis classifier AUC of 0.993

Abstract

This short paper reports the method and the evaluation results of Casio and Shinshu University joint team for the ISBI Challenge 2017 - Skin Lesion Analysis Towards Melanoma Detection - Part 3: Lesion Classification hosted by ISIC. Our online validation score was 0.958 with melanoma classifier AUC 0.924 and seborrheic keratosis classifier AUC 0.993.