BATseg脊髓肿瘤分割数据集
包含653名患者的钆增强T1加权3D MRI，覆盖星形胶质瘤、室管膜瘤、血管母细胞瘤和脊髓脑膜瘤，用于多类脊髓肿瘤分割。由The Hong Kong Polytechnic University; Capital Medical University提供，来自GitHub，包含医学影像数据，适用于图像分割任务，许可证为CC BY-NC-SA。
基本信息
资源简介
BATseg脊髓肿瘤分割数据集
【数据集背景】
本数据集源站标题为《vLAR-group/BATseg》。源站首次发布：2025-06-09。
【数据内容】
源站原始描述：## BATseg++: Boundary-aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans Hongkang Song, Zihui Zhang, Yanpeng Zhou, Jie Hu, Zishuo Wang, Hou Him Chan, Chon Lok Lei, Chen Xu, Yu Xin, Bo Yang ### Overview 1) We present the first and large-scale dataset for spinal cord tumor segmentation, comprising five prevalent tumor types from 940 patients. 2) We introduce a boundary-aware loss function that enables the network to delineate 3D surfaces of each spinal cord tumor subtype in MRI volume…
【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/vLAR-group/BATseg
使用许可：NOASSERTION。
【使用注意】
· 源站最后修改于 2025-12-12，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/vLAR-group/BATseg.git
curl -L -o repo.zip https://github.com/vLAR-group/BATseg/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
BATseg++: Boundary-aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans
Hongkang Song, Zihui Zhang, Yanpeng Zhou, Jie Hu, Zishuo Wang, Hou Him Chan, Chon Lok Lei, Chen Xu, Yu Xin, Bo Yang
<h4 align=“center”>
Overview
- We present the first and large-scale dataset for spinal cord tumor segmentation, comprising five prevalent tumor types from 940 patients.
- We introduce a boundary-aware loss function that enables the network to delineate 3D surfaces of each spinal cord tumor subtype in MRI volumes, enhancing segmentation accuracy by capturing surrounding structural details.
- We adopt a probabilistic tumor classification module to achieve accurate tumor type estimation.
The code of our method is developed based on the nnUNet.
1. Environment
-
Install PyTorch as described on their website.
-
Install BATseg:
git clone https://github.com/vLAR-group/BATseg.git cd BATseg pip install -e . pip install cupy-cuda11x blosc2 acvl_utils==0.2 MedPy -
Setting up Paths:
nnUNet relies on environment variables to know where raw data, preprocessed data and trained model weights are stored.
To use the full functionality of nnUNet, the following three environment variables must be set:-
nnUNet_raw: This is where you place the raw datasets. This folder will have one subfolder for each dataset names
DatasetXXX_YYY where XXX is a 3-digit identifier (such as 001, 002, 043, 999, …) and YYY is the (unique)
dataset name. The datasets must be in nnUNet format.Example tree structure:
nnUNet_raw/Dataset001_NAME1 ├── dataset.json ├── imagesTr │ ├── ... ├── imagesTs │ ├── ... └── labelsTr ├── ... nnUNet_raw/Dataset002_NAME2 ├── dataset.json ├── imagesTr │ ├── ... ├── imagesTs │ ├── ... └── labelsTr ├── ... -
nnUNet_preprocessed: This is the folder where the preprocessed data will be saved. The data will also be read from
this folder during training. It is important that this folder is located on
-
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。
