MILK10k:诊断色素性与非色素性皮肤癌及其模拟病变的分层多模态影像学习工具包
本研究介绍MILK10k多模态图像数据集,用于增强机器学习和人工智能驱动的可疑恶性皮肤肿瘤诊断。数据集包含来自5个中心5240例的10480张图像,覆盖48种ISIC匹配诊断,其中95.7%经活检或切除以组织病理学为金标准,并提供可解释概念评估流程与基准测试集。
要点
- MILK10k含10480张图像、5240例,覆盖48种ISIC匹配诊断。
- 95.7%病例经活检或切除,以组织病理学为金标准。
- 提供基于色素、溃疡、毛发等可解释概念的机器学习评估流程。
核心结论
- MILK10k数据集可支持皮肤病变机器学习与人工智能诊断应用,并覆盖色素性与非色素性、肿瘤性与非肿瘤性病变。
研究设计与样本
- 回顾性收集5个中心5240例的10480张图像,含近距离与皮肤镜图像,并附带年龄、性别、肤色、解剖部位和诊断等元数据。
主要发现
- 数据集覆盖48种ISIC匹配诊断,包含不同肤色个体及罕见皮肤病图像。
- 95.7%(n=5016)病例经活检或切除,组织病理学为金标准。
- 提供基于色素、溃疡、毛发和皮肤标记等人类可解释概念的机器学习流程评估结果。
- 提供来自相同来源的948张多模态图像基准测试集及在线工具,用于评估机器学习模型和人类阅片研究。
关键数值与推荐
- 数据集包含10480张图像,来自5240例,95.7%(n=5016)经活检或切除并以组织病理学为金标准。
- 覆盖48种ISIC匹配诊断,基准测试集含948张多模态图像。
临床怎么用
- 可用于开发和评估皮肤癌诊断的机器学习模型,尤其关注色素性与非色素性病变及不同肤色人群。
- 基准测试集和在线工具支持机器学习模型与人类阅片研究的标准化比较。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
In this study, we introduce MILK10k, a multimodal image dataset designed to enhance machine learning and artificial intelligence-driven applications for diagnosing skin lesions suspected to be malignant neoplasms. MILK10k includes both close-up and dermatoscopy images expanding upon existing datasets with several enhancements. It expands disease coverage to 48 International Skin Imaging Collaboration-Designated Diagnoses-matched diagnoses, encompassing both neoplastic and non-neoplastic as well as pigmented and nonpigmented skin lesions. In addition, MILK10k incorporates images from individuals with diverse skin tones as well as rare skin diseases. The dataset includes 10,480 images from 5240 cases, retrospectively collected across 5 different centers. Of these, 95.7% (n = 5016) have been biopsied or excised, with histopathology serving as the ground truth. Accompanying metadata includes information on age, sex, skin tone, anatomic site, and diagnosis with varying levels of granularity. In addition to the dataset, we provide results from a machine-learning pipeline that evaluates images on the basis of common, human-interpretable concepts such as pigmentation, ulceration, hair, and skin markings. Furthermore, we provide a benchmark test set of 948 multimodal images from the same sources and an online tool for assessing key metrics on this set, creating a platform for evaluating both machine-learning models and human reader studies.
引用
- Tschandl P, Akay BN, Rosendahl C, et al. MILK10k: A Hierarchical Multimodal Imaging-Learning Toolkit for Diagnosing Pigmented and Nonpigmented Skin Cancer and its Simulators. J Invest Dermatol. 2025. PMID: 40701400. doi:10.1016/j.jid.2025.06.1594
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。