Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations
Preprint
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.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Domain-specific classification-pretrained fully convolutional network encoders for skin lesion segmentationComputers in Biology and Medicine, 2019
- Segmentation of skin lesions in dermoscopy images using fuzzy classification of pixels and histogram thresholdingComputer Methods and Programs in Biomedicine, 2019
- Step-wise integration of deep class-specific learning for dermoscopic image segmentationPattern Recognition, 2019
- SLSDeep: Skin Lesion Segmentation Based on Dilated Residual and Pyramid Pooling Networks2018
- Melanoma recognition in dermoscopy images using lesion's peripheral region informationComputer Methods and Programs in Biomedicine, 2018
- Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networksComputer Methods and Programs in Biomedicine, 2018
- A survey on deep learning in medical image analysisMedical Image Analysis, 2017
- Automatic segmentation of dermoscopy images using saliency combined with Otsu thresholdComputers in Biology and Medicine, 2017
- Computational methods for the image segmentation of pigmented skin lesions: A reviewComputer Methods and Programs in Biomedicine, 2016
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009