ABIDE数据集
ABIDE数据集包含900名个体的fMRI数据，用于研究自闭症谱系障碍的脑功能网络差异。
基本信息
资源简介
ABIDE数据集
【数据集背景】
本数据集源站标题为《SjirSchielen/groupICAonABIDE》。源站首次发布：2024-11-05。
【数据内容】
源站原始描述：# groupICAonABIDE In this repository, the outputs of group independent component analysis (ICA) are presented together with the code used to preprocess the functional scans. ## Structure This repository is structured by two main folders: ''data'' and ''code''. ''data'' contains the output time series of dual regression, the output components of group ICA, and supporting files. More information can be found in the ''readMe'' file located in the ''data'' folder. ''code'' contains Matlab and Python code that w…
【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/SjirSchielen/groupICAonABIDE
使用许可：CC0-1.0。
【使用注意】
· 源站最后修改于 2025-03-28，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/SjirSchielen/groupICAonABIDE.git
curl -L -o repo.zip https://github.com/SjirSchielen/groupICAonABIDE/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
groupICAonABIDE
In this repository, the outputs of group independent component analysis (ICA) are presented together with the code used to preprocess the functional scans.
Structure
This repository is structured by two main folders: ‘‘data’’ and ‘‘code’’.
‘‘data’’ contains the output time series of dual regression, the output components of group ICA, and supporting files.
More information can be found in the ‘‘readMe’’ file located in the ‘‘data’’ folder.
‘‘code’’ contains Matlab and Python code that was used to preprocess ABIDE.
More information can be found in the ‘‘readMe’’ file located in the ‘‘code’’ folder.
Software versions
Matlab scripts were run in Matlab 2023b with SPM12.
FSL version 6.0 was run in Windows subsystem for Linux.
Zenodo DOI
10.5281/zenodo.15100690
https://doi.org/10.5281/zenodo.15100689
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。
需要用于商业化训练或医疗器械注册（NMPA/FDA）？
公开数据往往缺乏完整的病理回证与专家标注。千方医数集依托陕川双基地与超十家三甲医院直连，提供完全合规、去标识化、支持注册级质控的专病数据集交易服务。
