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

TL;DR

The HAM10000 dataset provides a large, diverse collection of dermatoscopic images of pigmented skin lesions, facilitating improved training and benchmarking of machine learning models for skin cancer diagnosis.

Contribution

This paper introduces the HAM10000 dataset, a large, multi-source dermatoscopic image collection with diverse acquisition methods, enabling better machine learning training and comparison with human experts.

Findings

Dataset contains 10015 images covering major pigmented lesion categories.

More than 50% of lesions are pathologically confirmed.

The dataset is publicly available for research and benchmarking.

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.