Identifying Melanoma Images using EfficientNet Ensemble: Winning Solution to the SIIM-ISIC Melanoma Classification Challenge

Qishen Ha, Bo Liu, Fuxu Liu

2020-10-11Medical Image Classification

Abstract

We present our winning solution to the SIIM-ISIC Melanoma Classification Challenge. It is an ensemble of convolutions neural network (CNN) models with different backbones and input sizes, most of which are image-only models while a few of them used image-level and patient-level metadata. The keys to our winning are: (1) stable validation scheme (2) good choice of model target (3) carefully tuned pipeline and (4) ensembling with very diverse models. The winning submission scored 0.9600 AUC on cross validation and 0.9490 AUC on private leaderboard.

Results

Task	Dataset	Metric	Value	Model
Classification	ISIC 2020 Challenge Dataset	AUC	0.949	EfficientNet Ensemble
Medical Image Classification	ISIC 2020 Challenge Dataset	AUC	0.949	EfficientNet Ensemble

Related Papers

FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise2025-07-13 Robust Training with Data Augmentation for Medical Imaging Classification2025-06-20 Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach2025-06-16 Detecção da Psoríase Utilizando Visão Computacional: Uma Abordagem Comparativa Entre CNNs e Vision Transformers2025-06-11 Recent Advances in Medical Image Classification2025-06-04 Deep Modeling and Optimization of Medical Image Classification2025-05-29 Advancements in Medical Image Classification through Fine-Tuning Natural Domain Foundation Models2025-05-26 EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion2025-05-23