既往移植后复发或难治性血液系统恶性肿瘤的再次移植

数据集获取

源站：https://clinicaltrials.gov/study/NCT02259348

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: Acute Lymphoblastic Leukemia (ALL), Acute Myeloid Leukemia (AML), Myeloid Sarcoma, Chronic Myelogenous Leukemia (CML), Juvenile Myelomonocytic Leukemia (JMML), Myelodysplastic Syndrome (MDS), Non-Hodgkin Lymphoma (NHL). PRIMARY OBJECTIVE: * To estimate engraftment by day +42 post-transplant in patients who receive CD45RA-depleted haploidentical donor progenitor cell transplantation following reduced intensity conditioning regimen that includes haploidentical natural killer (NK) cells. SECONDARY OBJECTIVES: * Estimate the incidence of malignant relapse, event-free survival, and overall survival at one-year post-transplantation. * Estimate incidence and severity of acute and chronic (GvHD). * Estimate the rate of transplant related mortality (TRM) in the first 100 days after transplantation. Blood progenitor cells will be collected from adult donors to be used for transplantation. Donor cells will be processed and filtered in a laboratory at St. Jude using a machine called the CliniMACS™ device, and later infused (transplanted) into the participant through his/her veins. Participants undergo a conditioning regimen beginning Day 21 prior to progenitor cell transplantation that includes chemotherapy medications and natural killer cells in preparation for transplantation. They will then receive T-cell depleted HPC transplant followed by CD45RA-depleted HPC transplant the following day.

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。