非肝硬化性门静脉高压自然史研究

数据集获取

源站：https://clinicaltrials.gov/study/NCT02417740

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, Immunologic Deficiency Syndrome, Turner Syndrome, Congenital Hepatic Fibrosis, Idiopathic Non-Cirrhotic Portal Hypertension. Study Description: Up to 400 subjects with noncirrhotic portal hypertension or at risk for developing noncirrhotic portal hypertension by virtue of their underlying disease (as well as sporadic cases of noncirrhotic portal hypertension as referred to in this protocol) will be offered inclusion in the study. Objectives: Primary Objective: 1. The goal of this natural history study is to generate understanding of the development and progression of NCPH. We will use our findings to generate novel biomarkers that will enable improved follow-up of patients, assist in preventing complications, and enhance transplant decision. Secondary Objectives: 1. Measurement of the bile acids and lipids to understand NCPH and porto-systemic shunting. 2. Identification of the genetic modifiers of NCPH. 3. Evaluation of hepatic transcriptome in absence and presence of NCPH. 4. Characterization of microbiome signatures in NCPH. Endpoints: Primary Endpoints: 1. Establish surveillance methods and guidelines for evaluation of NCPH. 2. Develop an understanding of the biological mechanisms of the progression of NCPH. 3. Identification of novel biomarkers correlating with NCPH progression. Secondary Endpoints: 1. Measurement of bile acids fractionated and total, as well as lipid panel to establish cut-off levels correlating with NCPH severity. 2. Establishment of positive or negative correlation between candidate susceptible genes and disease phenotype. 3. Identification of novel markers of fibrosis or the development of hepatic neoplasia from transcriptome analysis. 4. Characterization of microbiome signatures (taxonomic and functional), as well as identification of specific species.

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。