THUNDER
THUNDER是数字病理学瓦片级基准，涵盖16种癌症，用于评估基础模型的特征、鲁棒性和不确定性。
基本信息
资源简介
THUNDER
【数据集背景】
本数据集源站标题为《MICS-Lab/thunder》。源站首次发布：2025-05-15。
【数据内容】
源站原始描述：[NeurIPS25 D&B Spotlight] A tile-level histopathology image understanding benchmark # Tile-level Histopathology image Understanding benchmark **Published at NeurIPS 2025 Datasets and Benchmarks Track (Spotlight)** We introduce **THUNDER**, a comprehensive benchmark designed to rigorously compare foundation models across various downstream tasks in computational pathology. THUNDER enables the evaluation and analysis of feature representations, robustness, and uncertainty quantification of these m…
【主题与分类】
主题标签：benchmark、deep-learning、digital-pathology、foundation-models、histopathology。
【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/MICS-Lab/thunder
使用许可：CC-BY-4.0。
【使用注意】
· 源站最后修改于 2026-06-08，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/MICS-Lab/thunder.git
curl -L -o repo.zip https://github.com/MICS-Lab/thunder/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
Usage
To learn more about how to use thunder, please visit our documentation.
An API and command line interface (CLI) are provided to allow users to download datasets, models, and run benchmarks. The API is designed to be user-friendly and allows for easy integration into existing workflows. The CLI provides a convenient way to access the same functionality from the command line.
[!IMPORTANT]
Downloading supported foundation models: you will have to visit the Huggingface URL of supported models you wish to use in order to accept usage conditions.
<details>
<summary>List of Huggingface URLs</summary>
- UNI: https://huggingface.co/MahmoodLab/UNI
- UNI2-h: https://huggingface.co/MahmoodLab/UNI2-h
- Virchow: https://huggingface.co/paige-ai/Virchow
- Virchow2: https://huggingface.co/paige-ai/Virchow2
- H-optimus-0: https://huggingface.co/bioptimus/H-optimus-0
- H-optimus-1: https://huggingface.co/bioptimus/H-optimus-1
- GenBio-PathFM: https://huggingface.co/genbio-ai/genbio-pathfm
- CONCH: https://huggingface.co/MahmoodLab/CONCH
- TITAN/CONCHv1.5: https://huggingface.co/MahmoodLab/TITAN
- Phikon: https://huggingface.co/owkin/phikon
- Phikon2: https://huggingface.co/owkin/phikon-v2
- Hibou-b: https://huggingface.co/histai/hibou-b
- Hibou-L: https://huggingface.co/histai/hibou-L
- Midnight-12k: https://huggingface.co/kaiko-ai/midnight
- KEEP: https://huggingface.co/Astaxanthin/KEEP
- QuiltNet-B-32: https://huggingface.co/wisdomik/QuiltNet-B-32
- PLIP: https://huggingface.co/vinid/plip
- MUSK: https://huggingface.co/xiangjx/musk
- DINOv2-B: https://huggingface.co/facebook/dinov2-base
- DINOv2-L: https://huggingface.co/facebook/dinov2-large
- ViT-B: https://huggingface.co/google/vit-base-patch16-224-in21k
- ViT-L: https://huggingface.co/google/vit-large-patch16-224-in21k
- CLIP-B: https://huggingface.co/openai/clip-vit-base-patch32
- CLIP-L: https://huggingface.co/openai/clip-vit-large-patch14
</details>
API Usage
When using the API you can run the following code to download datasets, models and run a benchmark:
from thunder import benchmark
benchmark("phikon", "break_his", "knn")
CLI Usage
When using the CLI you can run the following command to see all available options,
thunder help
In order to reproduce the above example you can run the following command:
## 数据加载示例（图像类）
```python
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。
