慢性乙型肝炎不同治疗路径下的残留组织学疾病

数据集获取

源站：https://clinicaltrials.gov/study/NCT07843446

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: Chronic Hepatitis B. The study includes treatment-naïve adults with chronic hepatitis B who underwent pretreatment liver biopsy at two tertiary-care centers in Istanbul, Türkiye: Haydarpaşa Numune Training and Research Hospital and Göztepe Prof. Dr. Süleyman Yalçın City Hospital. Clinical, virological, biochemical, hematological, and histological data were obtained retrospectively from institutional records and existing databases. Pretreatment laboratory measurements obtained within 3 months before liver biopsy are used. Histological activity is assessed using the histological activity index (HAI), and fibrosis is staged according to the Ishak system. The primary histological outcome is significant histological disease, defined as HAI ≥6 and/or Ishak fibrosis stage ≥2. Four contemporary non-biopsy treatment pathways are retrospectively reconstructed using the variables available in the harmonized datasets: the WHO 2024 pathway, the EASL 2025 biochemical pathway, the APASL 2026 biochemical pathway, and an exploratory Turkish SUT pathway. These analyses do not represent complete implementation of all components of the respective guidelines because some clinical, liver-stiffness, longitudinal, fibrosis, and special-population criteria were not available in the retrospective datasets. The principal analyses evaluate treatment-pathway positivity and the prevalence of significant histological disease among pathway-negative patients. Additional analyses assess histological disease among pathway-positive patients, individual inflammatory and fibrosis components, agreement between pathways, between-center differences, a stricter composite histological definition, fibrosis alone, restriction to the calendar period common to both centers, and alternative ALT thresholds.

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。