Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model

TL;DR

This paper introduces a semi-supervised skin lesion segmentation method that effectively leverages unlabeled data through transformation consistency, achieving superior results with significantly fewer labeled samples.

Contribution

The novel semi-supervised approach uses transformation consistency in a self-ensembling model to improve skin lesion segmentation with limited labeled data.

Findings

Achieved state-of-the-art results with only 300 labeled samples

Surpassed fully-supervised methods trained with 2000 labeled samples

Enhanced regularization through transformation consistency

Abstract

Automatic skin lesion segmentation on dermoscopic images is an essential component in computer-aided diagnosis of melanoma. Recently, many fully supervised deep learning based methods have been proposed for automatic skin lesion segmentation. However, these approaches require massive pixel-wise annotation from experienced dermatologists, which is very costly and time-consuming. In this paper, we present a novel semi-supervised method for skin lesion segmentation by leveraging both labeled and unlabeled data. The network is optimized by the weighted combination of a common supervised loss for labeled inputs only and a regularization loss for both labeled and unlabeled data. In this paper, we present a novel semi-supervised method for skin lesion segmentation, where the network is optimized by the weighted combination of a common supervised loss for labeled inputs only and a regularization loss for both labeled and unlabeled data. Our method encourages a consistent prediction for unlabeled images using the outputs of the network-in-training under different regularizations, so that it can utilize the unlabeled data. To utilize the unlabeled data, our method encourages the consistent predictions of the network-in-training for the same input under different regularizations. Aiming for the semi-supervised segmentation problem, we enhance the effect of regularization for pixel-level predictions by introducing a transformation, including rotation and flipping, consistent scheme in our self-ensembling model. With only 300 labeled training samples, our method sets a new record on the benchmark of the International Skin Imaging Collaboration (ISIC) 2017 skin lesion segmentation challenge. Such a result clearly surpasses fully-supervised state-of-the-arts that are trained with 2000 labeled data.