Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)

Abstract

This work summarizes the results of the largest skin image analysis challenge in the world, hosted by the International Skin Imaging Collaboration (ISIC), a global partnership that has organized the world's largest public repository of dermoscopic images of skin. The challenge was hosted in 2018 at the Medical Image Computing and Computer Assisted Intervention (MICCAI) conference in Granada, Spain. The dataset included over 12,500 images across 3 tasks. 900 users registered for data download, 115 submitted to the lesion segmentation task, 25 submitted to the lesion attribute detection task, and 159 submitted to the disease classification task. Novel evaluation protocols were established, including a new test for segmentation algorithm performance, and a test for algorithm ability to generalize. Results show that top segmentation algorithms still fail on over 10% of images on average, and algorithms with equal performance on test data can have different abilities to generalize. This is an important consideration for agencies regulating the growing set of machine learning tools in the healthcare domain, and sets a new standard for future public challenges in healthcare.

arXiv commenthttps://challenge2018.isic-archive.com/

References in corpus (2)

• RECOD Titans at ISIC Challenge 2017
• Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for the Diagnosis of Skin Lesions

Cited by in corpus (103)

• U-Net and its variants for medical image segmentation: theory and applications
• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• Segment Anything Model for Medical Images?
• Metrics reloaded: Recommendations for image analysis validation
• MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
• Florence: A New Foundation Model for Computer Vision
• DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentation
• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• BCN20000: Dermoscopic Lesions in the Wild
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification
• H-vmunet: High-order Vision Mamba UNet for Medical Image Segmentation
• A Survey on Deep Learning for Skin Lesion Segmentation
• Transformers in Healthcare: A Survey
• UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation
• A survey, review, and future trends of skin lesion segmentation and classification
• Recent Progress in Transformer-based Medical Image Analysis
• The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classification
• TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• SLSNet: Skin lesion segmentation using a lightweight generative adversarial network
• Semi-supervised few-shot learning for medical image segmentation
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
• Enhancing Skin Disease Classification Leveraging Transformer-based Deep Learning Architectures and Explainable AI
• Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey
• Skin cancer detection based on deep learning and entropy to detect outlier samples
• Image Classification with Small Datasets: Overview and Benchmark
• Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms
• Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
• Interpretations are useful: penalizing explanations to align neural networks with prior knowledge
• Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images
• Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
• U-Net Using Stacked Dilated Convolutions for Medical Image Segmentation
• LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks
• Self-Supervised Learning For Few-Shot Image Classification
• Cross-Domain Few-Shot Learning by Representation Fusion
• Embedded Visual Prompt Tuning
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation
• Leveraging Adaptive Color Augmentation in Convolutional Neural Networks for Deep Skin Lesion Segmentation
• DONet: Dual Objective Networks for Skin Lesion Segmentation
• Handling Inter-Annotator Agreement for Automated Skin Lesion Segmentation
• A Broader Study of Cross-Domain Few-Shot Learning
• HST-MRF: Heterogeneous Swin Transformer with Multi-Receptive Field for Medical Image Segmentation
• An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
• Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models
• Multi-Compound Transformer for Accurate Biomedical Image Segmentation
• ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning
• Unsupervised Medical Image Segmentation with Adversarial Networks: From Edge Diagrams to Segmentation Maps
• Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification
• Self-Loop Uncertainty: A Novel Pseudo-Label for Semi-Supervised Medical Image Segmentation
• Y-net: Biomedical Image Segmentation and Clustering
• A CNN toolbox for skin cancer classification
• A Region of Interest Focused Triple UNet Architecture for Skin Lesion Segmentation
• Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
• Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data
• (De)Constructing Bias on Skin Lesion Datasets
• A Systematic Collection of Medical Image Datasets for Deep Learning
• Rethinking Supervised Pre-training for Better Downstream Transferring
• Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification
• IROF: a low resource evaluation metric for explanation methods
• Bluish Veil Detection and Lesion Classification using Custom Deep Learnable Layers with Explainable Artificial Intelligence (XAI)
• Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
• Visual Diagnosis of Dermatological Disorders: Human and Machine Performance
• Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
• Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection
• ESAI: Efficient Split Artificial Intelligence via Early Exiting Using Neural Architecture Search
• Semi-supervised Medical Image Classification with Global Latent Mixing
• MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
• Distribution Estimation to Automate Transformation Policies for Self-Supervision
• SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning
• SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
• Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
• Self-Learning AI Framework for Skin Lesion Image Segmentation and Classification
• MixModule: Mixed CNN Kernel Module for Medical Image Segmentation
• TricycleGAN: Unsupervised Image Synthesis and Segmentation Based on Shape Priors
• When Medical Imaging Met Self-Attention: A Love Story That Didn't Quite Work Out
• Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRI
• Dataset Distribution Impacts Model Fairness: Single vs. Multi-Task Learning
• Enhancing Mixup-based Semi-Supervised Learning with Explicit Lipschitz Regularization
• SkiNet: A Deep Learning Solution for Skin Lesion Diagnosis with Uncertainty Estimation and Explainability
• Lightweight Relational Embedding in Task-Interpolated Few-Shot Networks for Enhanced Gastrointestinal Disease Classification
• Streaming Self-Training via Domain-Agnostic Unlabeled Images
• Manifold-driven Attention Maps for Weakly Supervised Segmentation
• Revisiting Hidden Representations in Transfer Learning for Medical Imaging
• Noisy Label Classification using Label Noise Selection with Test-Time Augmentation Cross-Entropy and NoiseMix Learning
• DenseNet approach to segmentation and classification of dermatoscopic skin lesions images
• Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training
• Modular Adaptation for Cross-Domain Few-Shot Learning
• Improving Lesion Detection by exploring bias on Skin Lesion dataset
• A generic ensemble based deep convolutional neural network for semi-supervised medical image segmentation
• Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data
• Learning and Exploiting Interclass Visual Correlations for Medical Image Classification
• DAMSL: Domain Agnostic Meta Score-based Learning
• Automated dermatoscopic pattern discovery by clustering neural network output for human-computer interaction
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images
• Regularizing Explanations in Bayesian Convolutional Neural Networks
• Deep Bregman Divergence for Contrastive Learning of Visual Representations
• Towards glass-box CNNs
• Out of distribution detection for skin and malaria images
• Out-of-Distribution Detection for Dermoscopic Image Classification
• Exploring Content Based Image Retrieval for Highly Imbalanced Melanoma Data using Style Transfer, Semantic Image Segmentation and Ensemble Learning