The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions

Abstract

Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available datasets of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset. We collected dermatoscopic images from different populations acquired and stored by different modalities. Given this diversity we had to apply different acquisition and cleaning methods and developed semi-automatic workflows utilizing specifically trained neural networks. The final dataset consists of 10015 dermatoscopic images which are released as a training set for academic machine learning purposes and are publicly available through the ISIC archive. This benchmark dataset can be used for machine learning and for comparisons with human experts. Cases include a representative collection of all important diagnostic categories in the realm of pigmented lesions. More than 50% of lesions have been confirmed by pathology, while the ground truth for the rest of the cases was either follow-up, expert consensus, or confirmation by in-vivo confocal microscopy.

Cited by in corpus (99)

• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
• Disparities in Dermatology AI: Assessments Using Diverse Clinical Images
• Segment Anything Model for Medical Images?
• MedViT: A Robust Vision Transformer for Generalized Medical Image Classification
• Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set
• MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
• DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentation
• Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification
• Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using MobileNet
• A Survey on Deep Learning for Skin Lesion Segmentation
• Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma
• Medical Visual Question Answering: A Survey
• A survey, review, and future trends of skin lesion segmentation and classification
• Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentation
• Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey
• Recent Progress in Transformer-based Medical Image Analysis
• The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classification
• MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentation
• A survey of recent methods for addressing AI fairness and bias in biomedicine
• Deep neural network or dermatologist?
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging
• Early Melanoma Diagnosis with Sequential Dermoscopic Images
• Diagnostic Accuracy of Content Based Dermatoscopic Image Retrieval with Deep Classification Features
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• Deep Model with Siamese Network for Viability and Necrosis Tumor Assessment in Osteosarcoma
• Enhancing Skin Disease Classification Leveraging Transformer-based Deep Learning Architectures and Explainable AI
• Multi-class Skin Cancer Classification Architecture Based on Deep Convolutional Neural Network
• Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images
• Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview
• Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation
• Knowledge Distillation approach towards Melanoma Detection
• Contrastive Self-supervised Neural Architecture Search
• Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images
• Clinical Melanoma Diagnosis with Artificial Intelligence: Insights from a Prospective Multicenter Study
• CADICA: a new dataset for coronary artery disease detection by using invasive coronary angiography
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks
• Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention
• Is it enough to optimize CNN architectures on ImageNet?
• The (de)biasing effect of GAN-based augmentation methods on skin lesion images
• Derm-T2IM: Harnessing Synthetic Skin Lesion Data via Stable Diffusion Models for Enhanced Skin Disease Classification using ViT and CNN
• Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval
• Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class
• CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets
• Crowdsourcing Dermatology Images with Google Search Ads: Creating a Real-World Skin Condition Dataset
• Skin Cancer Classification using Inception Network and Transfer Learning
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• MUCM-Net: A Mamba Powered UCM-Net for Skin Lesion Segmentation
• Leveraging Adaptive Color Augmentation in Convolutional Neural Networks for Deep Skin Lesion Segmentation
• Is SAM 2 Better than SAM in Medical Image Segmentation?
• In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review
• An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
• FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image Recognition
• Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification
• Rethinking model prototyping through the MedMNIST+ dataset collection
• Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification
• FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
• FAA-CLIP: Federated Adversarial Adaptation of CLIP
• Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis
• Simulations of Common Unsupervised Domain Adaptation Algorithms for Image Classification
• Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpox
• Achieve Fairness without Demographics for Dermatological Disease Diagnosis
• A Region of Interest Focused Triple UNet Architecture for Skin Lesion Segmentation
• Automated skin lesion segmentation using multi-scale feature extraction scheme and dual-attention mechanism
• Uncertainty-Aware Segmentation Quality Prediction via Deep Learning Bayesian Modeling: Comprehensive Evaluation and Interpretation on Skin Cancer and Liver Segmentation
• Bluish Veil Detection and Lesion Classification using Custom Deep Learnable Layers with Explainable Artificial Intelligence (XAI)
• Skin Lesion Classification Using a Soft Voting Ensemble of Convolutional Neural Networks
• Pitfalls of Conformal Predictions for Medical Image Classification
• Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
• Analysis of Explainable Artificial Intelligence Methods on Medical Image Classification
• A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
• A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis
• Domain Adaptation Techniques for Natural and Medical Image Classification
• Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis
• Asymmetric Lesion Detection with Geometric Patterns and CNN-SVM Classification
• Adaptive Mix for Semi-Supervised Medical Image Segmentation
• Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm
• Pigment Network Detection and Classification in Dermoscopic Images Using Directional Imaging Algorithms and Convolutional Neural Networks
• PASSION for Dermatology: Bridging the Diversity Gap with Pigmented Skin Images from Sub-Saharan Africa
• Classification of Melanocytic Nevus Images using BigTransfer (BiT)
• Dataset Distribution Impacts Model Fairness: Single vs. Multi-Task Learning
• BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning
• Lightweight Relational Embedding in Task-Interpolated Few-Shot Networks for Enhanced Gastrointestinal Disease Classification
• AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model
• Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models
• Evaluating the Fairness of Neural Collapse in Medical Image Classification
• iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data
• A Multi-Scale Framework for Out-of-Distribution Detection in Dermoscopic Images
• Algorithmic Fairness Datasets: the Story so Far
• PET-TURTLE: Deep Unsupervised Support Vector Machines for Imbalanced Data Clusters
• Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
• Noisy Label Classification using Label Noise Selection with Test-Time Augmentation Cross-Entropy and NoiseMix Learning
• MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matching
• Contrastive meta-domain adaptation for robust skin lesion classification across clinical and acquisition conditions
• Unmasking Biases and Reliability Concerns in Convolutional Neural Networks Analysis of Cancer Pathology Images
• Contour Flow Constraint: Preserving Global Shape Similarity for Deep Learning based Image Segmentation
• Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning
• Automated dermatoscopic pattern discovery by clustering neural network output for human-computer interaction