自发性脑内出血水肿CT数据集

数据集获取（Figshare）

• 源站标题：PHE-SICH-CT-IDS
• DOI：10.6084/m9.figshare.23957937.v4
• 发布日期：2026-03-25
• 文件数：1 个
• 文件总体积：1.30 GB
• 源站页面：https://figshare.com/articles/dataset/PHE-SICH-CT-IDS/23957937

命令行下载

curl -L -o "PHE-SICH-CT-IDS.zip" "https://ndownloader.figshare.com/files/63081925"

文件清单

• PHE-SICH-CT-IDS.zip（1.30 GB）

文件总体积 1.30 GB（源站 API 实测）。

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。

数据说明

This publicly available dataset namely PHE-SICH-CT-IDS, which is constructed 120 CT scans of patients with spontaneous intracerebral hemorrhage. PHE-SICH-CT-IDS contains 3,511 CT images of SICH occurring in the basal ganglia region, with associated labels for the surrounding edematous zone around the hematoma. PHE-SICH-CT-IDS provides multiple functionalities including segmentation, detection, feature extraction, and more. It is divided into three sub-datasets representing different functionalities and formats: subdatasetA in NIfTI format, containing source CT data and edema zone labels, offering segmentation, feature extraction and prognosis prediction functionalities; subdatasetB and subdatasetC in JPG and PNG formats, containing sliced data with segmentation labels and detection annotations, providing segmentation and detection functionalities.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.23957937.v4（source: https://figshare.com/articles/dataset/PHE-SICH-CT-IDS/23957937）。