Araguaia Medical Vision Lab at ISIC 2017 Skin Lesion Classification Challenge

This paper describes the participation of Araguaia Medical Vision Lab at the International Skin Imaging Collaboration 2017 Skin Lesion Challenge. We describe the use of deep convolutional neural networks in attempt to classify images of Melanoma and Seborrheic Keratosis lesions. With use of finetuned GoogleNet and AlexNet we attained results of 0.950 and 0.846 AUC on Seborrheic Keratosis and Melanoma respectively. Keywords—IEEEtran, journal, LTEX, paper, template. I. MOTIVATION AND OVERVIEW This paper is a small overview of Araguaia Medical Vision Lab (AMVL) at the International Skin Imaging Collaboration (ISIC) 2017 challenge, more specifically the skin lesion classification task. Our main objective is to perform an automatic classification of skin lesions on two main tasks, the Melanoma and Seborrheic Keratosis recognition, using the image dataset available by ISIC, which was already diagnosed by specialists and used as ground truth. The algorithm proposed a combination of deep convolutional neural networks (CNN), GoogleNet[1] and AlexNet[2], fine-tuned [3] with augmented skin lesion images. The next sessions will describe how was the training and evaluation process. II. IMAGE PRE-PROCESSING The original dataset is composed by 2000 images, with 374 samples of Melanoma and 254 samples of Seborrheic Keratosis, the other 1372 are defined as Nevus. The images have different sizes from 1022 x 767 to 6748 x 4499. The first step was split a validation set with around 20% of images from each class to evaluate the neural network performance during the training stage. All train dataset pass through a pre-process filter which applied random shear, zoom, and vertical and horizontal shift and flip. This step was necessary to increase the dataset size (around 5 times), make it less unbalanced and improve the neural network accuracy. III. NETWORK TRAINING AND EVALUATION To perform all the training and evaluation we used Nvidia Digits interface running with Caffe [4]. A. Seborrheic Keratosis Task On Seborrheic classification task we got the best result resizing all training images to 350 x 350 without losing proportions and training an AlexNet pre-trained on ImageNet classification task dataset by the Berkeley Vision and Learning Center (ref). The network was trained over 30 epochs with a Stochastic Gradient Descent (SGD) using three stages, first 10 epochs with learning rate of 0.001, than 10 epochs with 0.0001, and 10 more with 0.00001. The top accuracy on validation set was 98.2%, with 97.73% on Seborrheic class and 98.28% on non-Seborrheic. On validation dataset from ISIC the network we got 89.3% accuracy and 0.950 of Area under Roc Curve (AUC), with sensibility of 0.786 and specificity of 0.935.