A Survey on Deep Learning for Skin Lesion Segmentation

Abstract

Skin cancer is a major public health problem that could benefit from computer-aided diagnosis to reduce the burden of this common disease. Skin lesion segmentation from images is an important step toward achieving this goal. However, the presence of natural and artificial artifacts (e.g., hair and air bubbles), intrinsic factors (e.g., lesion shape and contrast), and variations in image acquisition conditions make skin lesion segmentation a challenging task. Recently, various researchers have explored the applicability of deep learning models to skin lesion segmentation. In this survey, we cross-examine 177 research papers that deal with deep learning-based segmentation of skin lesions. We analyze these works along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules, and losses), and evaluation aspects (data annotation requirements and segmentation performance). We discuss these dimensions both from the viewpoint of select seminal works, and from a systematic viewpoint, examining how those choices have influenced current trends, and how their limitations should be addressed. To facilitate comparisons, we summarize all examined works in a comprehensive table as well as an interactive table available online at https://github.com/sfu-mial/skin-lesion-segmentation-survey.

Published in Medical Image Analysis (2023); 55 pages, 10 figures; Mirikharaji and Abhishek: Joint first authors; Celebi and Hamarneh: Joint senior authors

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Rethinking Atrous Convolution for Semantic Image Segmentation
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Domain-adversarial neural networks to address the appearance variability of histopathology images
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• Lesion Border Detection in Dermoscopy Images
• Leakage and the Reproducibility Crisis in ML-based Science
• MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation
• Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation
• Extraction of Skin Lesions from Non-Dermoscopic Images Using Deep Learning
• Transformers in Medical Image Analysis: A Review
• An Improved Objective Evaluation Measure for Border Detection in Dermoscopy Images
• Hyper-Fusion Network for Semi-Automatic Segmentation of Skin Lesions
• Approximate Lesion Localization in Dermoscopy Images
• DONet: Dual Objective Networks for Skin Lesion Segmentation
• Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging
• Lesion Net -- Skin Lesion Segmentation Using Coordinate Convolution and Deep Residual Units
• MixModule: Mixed CNN Kernel Module for Medical Image Segmentation
• Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation

Cited by in corpus (4)

• A survey, review, and future trends of skin lesion segmentation and classification
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging
• In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review