囊性纤维化家庭非结核分枝杆菌环境储源研究

数据集获取

源站：https://clinicaltrials.gov/study/NCT07369414

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: Cystic Fibrosis (CF), Mucoviscidosis, Non-Tuberculous Mycobacteria, Mycobacterium Abscessus Infection. This multicenter, non-interventional case-control study investigates whether domestic environmental reservoirs-particularly household water systems-contribute to non-tuberculous mycobacterial (NTM) infections in people with cystic fibrosis (CF). Approximately 120 CF patients from several centers in Germany will be enrolled, including 60 patients with a current or previous pulmonary NTM infection and 60 CF patients without known NTM infection as controls. Environmental samples (water, dust, and soil) will be collected from participants’ households and analyzed for the presence of NTM using culture-based methods, PCR, and whole-genome sequencing. These findings will be compared between case and control households, and genetic similarity between environmental NTM isolates and available clinical isolates from the same patients will be assessed. In addition, standardized questionnaires will capture environmental and behavioral risk factors associated with NTM occurrence. The study is purely observational and relies on clinical data and isolates obtained through routine CF care, with no additional medical procedures for participants. Over a follow-up period of up to three years, newly occurring NTM infections in initially unaffected patients will be documented. The results aim to improve understanding of environmental exposure risks for NTM in CF and to provide evidence for future prevention strategies and potential guideline recommendations.

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。