CAD4TB验证研究（坦桑尼亚IHI）

数据集获取（Figshare）

• 源站标题：CAD4TB validation study IHI Tanzania
• DOI：10.6084/m9.figshare.936571.v1
• 发布日期：2014-02-16
• 文件数：1 个
• 文件总体积：77.52 KB
• 源站页面：https://figshare.com/articles/dataset/CAD4TB_validation_study_IHI_Tanzania/936571

命令行下载

curl -L -o "CAD4TB IHI 2013.xlsx" "https://ndownloader.figshare.com/files/1388318"

文件清单

• CAD4TB IHI 2013.xlsx（77.52 KB）

文件总体积 77.52 KB（源站 API 实测）。

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。

数据说明

CAD4TB is an automated reading software for the detection of active pulmonary tuberculosis on chest radiographs. Its output is an abnormality score between 0 - 100. We evaluated the performance of version 3.07 (updated) on a set of 861 presumptive TB patients enrolled in the TB Cohort and TB CHILD studies at Ifakara Health Institute, Bagamoyo, Tanzania. Culture-confirmed pumonary tuberculosis was used as the positive reference standard. Two human readers (one expert and one clinical officer) interpreted the same set of images. Performance of human and automated reading was compared.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.936571.v1（source: https://figshare.com/articles/dataset/CAD4TB_validation_study_IHI_Tanzania/936571）。