Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting

Abstract

In this paper we present the methods of our submission to the ISIC 2018 challenge for skin lesion diagnosis (Task 3). The dataset consists of 10000 images with seven image-level classes to be distinguished by an automated algorithm. We employ an ensemble of convolutional neural networks for this task. In particular, we fine-tune pretrained state-of-the-art deep learning models such as Densenet, SENet and ResNeXt. We identify heavy class imbalance as a key problem for this challenge and consider multiple balancing approaches such as loss weighting and balanced batch sampling. Another important feature of our pipeline is the use of a vast amount of unscaled crops for evaluation. Last, we consider meta learning approaches for the final predictions. Our team placed second at the challenge while being the best approach using only publicly available data.

arXiv commentISIC Skin Image Analysis Workshop and Challenge @ MICCAI 2018. Second place at challenge, best with public data, see https://challenge2018.isic-archive.com/leaderboards/

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• A Survey on Deep Learning in Medical Image Analysis
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• RECOD Titans at ISIC Challenge 2017
• Dual Path Networks

Cited by in corpus (7)

• Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification
• Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting
• The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classification
• Interpretable Deep Learning under Fire
• Recent advances in deep learning applied to skin cancer detection
• Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification
• Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models