CVMar 9, 2017

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

arXiv:1703.03108v1174 citations
Originality Synthesis-oriented
AI Analysis

This work addresses skin cancer detection for medical diagnosis, but it is incremental as it applies existing ensemble methods to a specific challenge dataset.

The paper tackled the problem of classifying skin lesions into melanoma, nevus, and seborrheic keratosis using a deep neural network ensemble, achieving an online validation score of 0.958 with AUCs of 0.924 for melanoma and 0.993 for seborrheic keratosis.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes