THUNDER

Name: THUNDER
Creator: CentraleSupelec, IHU-National PRecISion Medicine Center in Oncology, LIVIA, ILLS, ETS Montreal, ILLS, MILA, Université Paris-Saclay, CNRS, CentraleSupélec

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。

CentraleSupelec, IHU-National PRecISion Medicine Center in Oncology, LIVIA, ILLS, ETS Montreal, ILLS, MILA, Université Paris-Saclay, CNRS, CentraleSupélec

arXiv

2025-07-10 更新

医学影像癌症医学影像

基本信息

模态

医学影像

创建/更新时间

2025-07-10

资源简介

THUNDER是一个用于数字病理学基础模型评估的瓦片级基准数据集，包含16种不同癌症类型的病理图像，支持多种任务如特征空间比较、鲁棒性和不确定性分析，旨在高效比较多种模型。

原始链接

https://github.com/MICS-Lab/thunder

arXiv 论文 →

访问原始数据

官方服务

如需原始数据获取支持或标注服务，请联系我们。

帮我联系

下载信息

注册下载

Tips: 该数据集需要在对应的数据源网站注册通过后，才能进行数据下载，注册有对应要求，或者需要收费。

暂未开放

公开下载

Tips: 该数据集属于公开下载，应该可以免费公开下载。

免登录

有偿下载

Tips: 该数据集 Qianfanghub 可以协助提供有偿下载服务，注意，服务不针对数据相关产权，只是技术服务费。

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

千方医数集，医疗数据集部分，是为社区服务的公开医疗数据集搜索引擎，并不存储或者下载原始的任何数据。如果您有其他医疗数据需求，可以和客服联系，或者下工单。我们有强大的三甲医疗机构帮助您提供个性化的医疗数据定制、采集、标注服务。

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