Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations

TL;DR

This paper introduces a multi-scale CNN framework with domain-specific augmentations for skin lesion segmentation and attribute detection, significantly improving performance on multiple ISIC datasets and achieving top rankings.

Contribution

It presents a novel transfer learning-based encoder-decoder architecture with multi-scale feature integration and specialized augmentations for enhanced skin lesion segmentation.

Findings

Outperforms state-of-the-art methods on ISIC2016 and ISIC2017 datasets.

Achieves first place on ISIC2018 attribute detection leaderboard.

Demonstrates the effectiveness of domain-specific augmentations in improving model generalization.

Abstract

Computer-aided diagnosis systems for classification of different type of skin lesions have been an active field of research in recent decades. It has been shown that introducing lesions and their attributes masks into lesion classification pipeline can greatly improve the performance. In this paper, we propose a framework by incorporating transfer learning for segmenting lesions and their attributes based on the convolutional neural networks. The proposed framework is based on the encoder-decoder architecture which utilizes a variety of pre-trained networks in the encoding path and generates the prediction map by combining multi-scale information in decoding path using a pyramid pooling manner. To address the lack of training data and increase the proposed model generalization, an extensive set of novel domain-specific augmentation routines have been applied to simulate the real variations in dermoscopy images. Finally, by performing broad experiments on three different data sets obtained from International Skin Imaging Collaboration archive (ISIC2016, ISIC2017, and ISIC2018 challenges data sets), we show that the proposed method outperforms other state-of-the-art approaches for ISIC2016 and ISIC2017 segmentation task and achieved the first rank on the leader-board of ISIC2018 attribute detection task.