Automatic Skin Lesion Analysis using Large-scale Dermoscopy Images and Deep Residual Networks

Abstract

Malignant melanoma has one of the most rapidly increasing incidences in the world and has a considerable mortality rate. Early diagnosis is particularly important since melanoma can be cured with prompt excision. Dermoscopy images play an important role in the non-invasive early detection of melanoma [1]. However, melanoma detection using human vision alone can be subjective, inaccurate and poorly reproducible even among experienced dermatologists. This is attributed to the challenges in interpreting images with diverse characteristics including lesions of varying sizes and shapes, lesions that may have fuzzy boundaries, different skin colors and the presence of hair [2]. Therefore, the automatic analysis of dermoscopy images is a valuable aid for clinical decision making and for image-based diagnosis to identify diseases such as melanoma [1-4]. Deep residual networks (ResNets) has achieved state-of-the-art results in image classification and detection related problems [5-8]. In this ISIC 2017 skin lesion analysis challenge [9], we propose to exploit the deep ResNets for robust visual features learning and representations.

Submission for ISIC2017 Challenge

References in corpus (3)

• Wide Residual Networks
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
• Automatic Detection of Blue-White Veil and Related Structures in Dermoscopy Images

Cited by in corpus (17)

• BCN20000: Dermoscopic Lesions in the Wild
• Data Augmentation for Skin Lesion Analysis
• The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classification
• Convolutional Sparse Kernel Network for Unsupervised Medical Image Analysis
• Transformation Consistent Self-ensembling Model for Semi-supervised Medical Image Segmentation
• Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations
• Data, Depth, and Design: Learning Reliable Models for Skin Lesion Analysis
• Star Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation
• A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification
• Deeply Supervised Rotation Equivariant Network for Lesion Segmentation in Dermoscopy Images
• Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images
• Automated skin lesion segmentation using multi-scale feature extraction scheme and dual-attention mechanism
• An Active Learning Approach for Reducing Annotation Cost in Skin Lesion Analysis
• Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks
• Improving Dermoscopic Image Segmentation with Enhanced Convolutional-Deconvolutional Networks
• Semi-supervised learning for medical image classification using imbalanced training data
• The Effects of Image Pre- and Post-Processing, Wavelet Decomposition, and Local Binary Patterns on U-Nets for Skin Lesion Segmentation