Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks

TL;DR

This paper presents a deep learning approach using fully convolutional networks for multi-class segmentation of skin lesions, achieving promising results on the ISIC-2017 dataset for melanoma, naevus, and keratosis.

Contribution

It introduces an end-to-end FCN-based method with transfer learning and hybrid loss for multi-class skin lesion segmentation, which is novel compared to prior single-class approaches.

Findings

Best Dice score of 78.5% for naevus

Segmentation accuracy of 84.62% for melanoma recognition

Effective multi-class segmentation with transfer learning

Abstract

Melanoma is clinically difficult to distinguish from common benign skin lesions, particularly melanocytic naevus and seborrhoeic keratosis. The dermoscopic appearance of these lesions has huge intra-class variations and high inter-class visual similarities. Most current research is focusing on single-class segmentation irrespective of classes of skin lesions. In this work, we evaluate the performance of deep learning on multi-class segmentation of ISIC-2017 challenge dataset, which consists of 2,750 dermoscopic images. We propose an end-to-end solution using fully convolutional networks (FCNs) for multi-class semantic segmentation to automatically segment the melanoma, seborrhoeic keratosis and naevus. To improve the performance of FCNs, transfer learning and a hybrid loss function are used. We evaluate the performance of the deep learning segmentation methods for multi-class segmentation and lesion diagnosis (with post-processing method) on the testing set of the ISIC-2017 challenge dataset. The results showed that the two-tier level transfer learning FCN-8s achieved the overall best result with \textit{Dice} score of 78.5% in a naevus category, 65.3% in melanoma, and 55.7% in seborrhoeic keratosis in multi-class segmentation and Accuracy of 84.62% for recognition of melanoma in lesion diagnosis.