Fully Convolutional Networks to Detect Clinical Dermoscopic Features

Abstract

We use a pretrained fully convolutional neural network to detect clinical dermoscopic features from dermoscopy skin lesion images. We reformulate the superpixel classification task as an image segmentation problem, and extend a neural network architecture originally designed for image classification to detect dermoscopic features. Specifically, we interpolate the feature maps from several layers in the network to match the size of the input, concatenate the resized feature maps, and train the network to minimize a smoothed negative F1 score. Over the public validation leaderboard of the 2017 ISIC/ISBI Lesion Dermoscopic Feature Extraction Challenge, our approach achieves 89.3% AUROC, the highest averaged score when compared to the other two entries. Results over the private test leaderboard are still to be announced.