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

TL;DR

LesionSeg introduces a deep convolutional neural network with innovative architectural features for accurate skin lesion segmentation, achieving competitive results on the ISIC 2017 challenge.

Contribution

The paper presents a novel end-to-end FCN architecture with atrous convolutions, network-in-network layers, and super-resolution upsampling for skin lesion segmentation.

Findings

Achieved mean IOU of 0.642 on validation set

Utilized atrous convolutions for larger receptive field

Incorporated super-resolution upsampling techniques

Abstract

We present a method for skin lesion segmentation for the ISIC 2017 Skin Lesion Segmentation Challenge. Our approach is based on a Fully Convolutional Network architecture which is trained end to end, from scratch, on a limited dataset. Our semantic segmentation architecture utilizes several recent innovations in particularly in the combined use of (i) use of atrous convolutions to increase the effective field of view of the network's receptive field without increasing the number of parameters, (ii) the use of network-in-network $1\times1$ convolution layers to add capacity to the network and (iii) state-of-art super-resolution upsampling of predictions using subpixel CNN layers. We reported a mean IOU score of 0.642 on the validation set provided by the organisers.