数据集获取

git clone https://github.com/intra3d2019/IntrA.git

curl -L -o repo.zip https://github.com/intra3d2019/IntrA/archive/refs/heads/master.zip
unzip repo.zip

源站 README 摘录（使用方式）

News

2020.04.06 Paper is updated, and Supplementary material is uploaded.
2020.03.02 Paper is uploaded to arXiv.

IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning (CVPR 2020 Oral)

Instead of 2D medical images, we introduce an open-access 3D intracranial aneurysm dataset, IntrA, that makes the application of points-based and mesh-based classification and segmentation models available. Our dataset can be used to diagnose intracranial aneurysms and to extract the neck for a clipping operation in medicine and other areas of deep learning, such as normal estimation and surface reconstruction.
The dataset could be download here.
We are grateful for adding your information on this form, if you think this dataset is useful.
Thank you!

Data

103 3D models of entire brain vessels are collected by reconstructing scanned 2D MRA images of patients. We do not publish the raw 2D MRA images because of medical ethics.

1909 blood vessel segments are generated automatically from the complete models, including 1694 healthy vessel segments and 215 aneurysm segments for diagnosis.

116 aneurysm segments are divided and annotated manually by medical experts; the scale of each aneurysm segment is based on the need for a preoperative examination.

Geodesic distance matrices are computed and included for each annotated 3D segment, because the expression of the geodesic distance is more accurate than Euclidean distance according to the shape of vessels.

Tools

Annotation

<img src=“images/ann_tool.jpg” alt=“ann_tool” align=“middle” width=“600”/>

annotation/main.py

Add button: adding a boundary line.

Left mouse button: selecting the points of a boundary line.

Middle mouse button: selecting a start point.

Vessel segment generation

random_pick.py
selection.py

Visualization

show_ann_data.py
show_result.py

Benchmark

Classification

<img src=“images/cls-re.png” alt=“ann_tool” align=“middle” width=“400”/>

Segmentation

<img src=“images/seg-re.png” alt=“ann_tool” align=“middle” width=“800”/>

Acknowledgements

This research was supported by AMED under Grant

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。

完整仓库：github.com/intra3d2019/IntrA