Fitzpatrick17k皮肤病图像数据集
Fitzpatrick17k皮肤病图像数据集收录按Fitzpatrick肤色分层的皮肤病图像、标签和公平性评估元数据，数据模态为图像，适合多汗症相关病例识别、诊断建模、分割检测、风险评估或临床研究复现。
基本信息
资源简介
Fitzpatrick17k皮肤病图像数据集
【数据集背景】
本数据集源站标题为《mattgroh/fitzpatrick17k》。源站首次发布：2021-04-15。
【数据内容】
源站原始描述：# Fitzpatrick17k ## Overview We annotated 16,577 clinical images sourced from two dermatology atlases — DermaAmin and Atlas Dermatologico — with Fitzpatrick skin type labels with two data annotation services: Scale AI and Centaur Labs. The Fitzpatrick labeling system, while not perfect, is a six-point scale originally developed for classifying sun reactivity of skin phenotype. The Fitzpatrick scale served as the basis for skin color in emojis and, more recently, the Fitzpatrick scal…
【适用方向】
影像类数据可用于医学图像分析模型（检测、分割、分类）的训练与评测，也可用于标注质量与成像参数相关性的研究。
【获取与许可】
源站页面：https://github.com/mattgroh/fitzpatrick17k
【使用注意】
· 源站最后修改于 2026-03-05，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取
git clone https://github.com/mattgroh/fitzpatrick17k.git
curl -L -o repo.zip https://github.com/mattgroh/fitzpatrick17k/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
Data Usage
Download the dataset
You can find the Fitzpatrick annotations in fitzpatrick17k.csv. You can download the images from their original source, which is shared in the url column of the Fitzpatrick annotations .csv. However, some of the links are broken. As an alternative, please fill out this form and contact us and we can provide a link to all the images.
Replicate our analysis
The results from our paper can be replicated using train.py and ita_fitzpatrick_analysis.ipynb.
After you download the dataset, edit train.py by specifying the image directory of the dataset, and then run python train.py 20 full where 20 refers to the number of epochs and full refers to the full dataset.
You can check out our comparison of Fitzpatrick annotations and individual typology angle scores with the ita_fitzpatrick_analysis.ipynb
How to cite this dataset and paper
@inproceedings{groh2021evaluating,
title={Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset},
author={Groh, Matthew and Harris, Caleb and Soenksen, Luis and Lau, Felix and Han, Rachel and Kim, Aerin and Koochek, Arash and Badri, Omar},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={18201828},
year={2021}
}
And the second paper:
@article{groh2022towards,
title={Towards transparency in dermatology image datasets with skin tone annotations by experts, crowds, and an algorithm},
author={Groh, Matthew and Harris, Caleb and Daneshjou, Roxana and Badri, Omar and Koochek, Arash},
journal={Proceedings of the ACM on Human-Computer Interaction},
volume={6},
number={CSCW2},
pages={126},
year={2022},
publisher={ACM New York, NY, USA}
}
数据加载示例（图像类）
from PIL import Image
import glob, os
files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)
# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path) # 要求 子目录=类别
目录组织与标注格式以源站说明和下载后实际文件为准。
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
