欧洲新诊断骨髓增生异常综合征患者前瞻性多中心注册研究

数据集获取

源站：https://clinicaltrials.gov/study/NCT00600860

标准获取流程：

1. 访问源站链接，注册/登录账号；
2. 进入数据集详情页，按页面指引申请权限或直接下载；
3. 部分平台提供 SDK，例如：
   • OpenDataLab: pip install openxlab 后 openxlab.dataset.get(...)
   • ModelScope: pip install modelscope 后 modelscope download
   • 天池: 登录后页面提供直链下载
     以源站「数据下载/使用文档」页面为准。

数据说明

Conditions: Myelodysplastic Syndromes (MDS). Methodology: Data on patients with MDS will be collected prospectively at diagnosis and at 6-months intervals after diagnosis. The data will be gathered by seventeen (or more) countries that are represented within the LeukemiaNet MDS Working Party and will be combined in one central European Database. Data analyses will be conducted by the Data Management Centre at the University of York in various sub studies, at specific time points as decided or requested by the steering committee, but at least once a year included in the European Registry and at the end of the follow-up period. Number of Patients & Centres Over 149 hematology centres in eighteen (or more) different countries (Austria, Croatia, Czech Republic, Denmark, France, Germany, Greece, Israel, Italy, The Netherlands, Romania, Spain, Sweden, Switzerland and United Kingdom) will participate as referral centres in this Registry. The recruitment target is a minimum of 3000 cases lower-risk MDS and 1000 higher-risk cases. Population: The study population will consist of newly diagnosed patients with all subtypes of MDS classified according to the WHO criteria, including therapy-related MDS and MDS-F, AML with 20-<30 percent marrow blasts (former RAEB-t), and CMML and other forms of mixed MDS/MPD. Study Duration: The enrolment time is scheduled to continue until at least December 2022 but extension of the recruitment period is possible. Patients will be followed until withdrawal (for any reason) or termination of the EUMDS Registry.

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。