Pacritinib联合低剂量地西他滨治疗中高危骨髓纤维化或MPN/MDS

数据集获取

源站：https://clinicaltrials.gov/study/NCT02564536

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 Myelomonocytic Leukemia, Juvenile Myelomonocytic Leukemia, Atypical Chronic Myeloid Leukemia, Myeloproliferative Neoplasm, Myelodysplastic Syndromes, Myelofibrosis. For the first 28 day cycle, all patients will be treated with single agent pacritinib at 200 mg twice daily. The investigators chose this starting dose based on the previous three phase I studies of pacritinib as a single agent which showed that the maximum tolerated dose (MTD) to be 500 mg, and subsequently, the dose of 400 mg daily was recommended for the phase II studies. Recently, the results of the phase III PERSIST-1 trial comparing pacritinib to best available therapy (BAT) in patients with MF was reported at the 2015 American Society of Clinical Oncology (ASCO) annual meeting. Pacritinib was found to be significantly more effective than BAT at reducing spleen volume at 24 weeks of therapy and improving constitutional symptoms. Low dose decitabine has demonstrated depletion of DNMT1 in normal hematopoietic stem cells (HSC) without cytotoxicity and subcutaneous (SC) instead of intravenous (IV) administration may avoid high peak levels that can cause apoptosis. Furthermore, the low toxicity associated with low dose decitabine would allow for more frequent (1 to 3 times weekly) administration of the drug which would catch more cells in S-phase via greater exposure time. Based on these findings, a starting dose of decitabine 5 mg/m2 SC twice weekly should be well tolerated and effective in patients with MF and MPN/MDS syndromes when combined with pacritinib 400 mg daily.

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。