LesionSeg: Semantic segmentation of skin lesions using Deep Convolutional Neural Network

We present a method for skin lesion segmentation for the ISIC 2017 Skin Lesion Segmentation Challenge. Our approach is based on a Fully Convolutional Neural Network architecture which is trained end to end, from scratch, on a small dataset. Our semantic segmentation architecture utilizes several recent innovations in deep learning particularly in the combined use of (i) atrous convolutions to increase the effective field of view of the network’s receptive field without increasing the number of parameters, (ii) tnetwork-in-network 1× 1 convolution layers to increase network capacity without increasing the number of parameters and (iii) state-of-art super-resolution upsampling of predictions using subpixel CNN layers for accurate and efficient upsampling of predictions. We achieved a IOU score of 0.642 on the validation set provided by the organisers.