基于CAD4TB人工智能的印度尼西亚受试者胸部X线肺结核预测数据（发表用数据）

数据集获取（Figshare）

• 源站标题：Pulmonary tuberculosis prediction using CAD4TB artificial intelligence (computer-aided detection for tuberculosis) based on thoracic x-ray photos among Indonesian subjects in hospital - Data for Publication
• DOI：10.6084/m9.figshare.29142734.v2
• 发布日期：2025-10-30
• 文件数：9 个
• 文件总体积：2.55 MB
• 源站页面：https://figshare.com/articles/dataset/Pulmonary_tuberculosis_prediction_using_CAD4TB_artificial_intelligence_computer-aided_detection_for_tuberculosis_based_on_thoracic_x-ray_photos_among_Indonesian_subjects_in_hospital_-_Data_for_Publication/29142734

命令行下载

curl -L -o "RAIT_Data for Publication_Coded.xlsx" "https://ndownloader.figshare.com/files/59144366"
curl -L -o "Output New Dataset - 20251020.spv" "https://ndownloader.figshare.com/files/59187932"
curl -L -o "New Dataset - 20251020.sav" "https://ndownloader.figshare.com/files/59187935"
curl -L -o "Hasil Analisis 20241211.spv" "https://ndownloader.figshare.com/files/59187938"
curl -L -o "RAIT Analysis_20241212" "https://ndownloader.figshare.com/files/59187944"
curl -L -o "RAIT Analysis_Sensitivity Based on Reference_20251020" "https://ndownloader.figshare.com/files/59187947"
curl -L -o "agreestat360report AFB-MRD.pdf" "https://ndownloader.figshare.com/files/59187968"
curl -L -o "agreestat360report AFB-Culture.pdf" "https://ndownloader.figshare.com/files/59187974"

文件清单

• RAIT_Data for Publication_Coded.xlsx（281.51 KB）
• Output New Dataset - 20251020.spv（157.22 KB）
• New Dataset - 20251020.sav（64.67 KB）
• Hasil Analisis 20241211.spv（867.41 KB）
• RAIT Analysis_20241212（589.80 KB）
• RAIT Analysis_Sensitivity Based on Reference_20251020（318.25 KB）
• agreestat360report AFB-MRD.pdf（90.74 KB）
• agreestat360report AFB-Culture.pdf（90.85 KB）
• agreestat360report MRD-Culture.pdf（90.86 KB）

文件总体积 2.55 MB（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

Tuberculosis is still one of the world’s leading infectious diseases, especially in countries like Indonesia where many cases go undetected due to limited access to expert medical imaging professionals. In this study, we explored whether a computer system called CAD4TB, which uses artificial intelligence to read chest X-rays, could help identify people with tuberculosis in a hospital setting. We compared its performance to experienced radiologists and used laboratory tests to confirm the results. We found that CAD4TB was able to detect tuberculosis with similar accuracy to human experts in many cases, especially among patients without complications like fluid in the lungs. Although expert radiologists remain slightly more accurate overall, CAD4TB performed well enough to suggest that it could be used to support hospital teams—especially where there are not enough trained readers. Because this system can analyze X-rays quickly and consistently, we believe it could be useful in busy hospitals and in regions with high numbers of tuberculosis cases. Our findings may help health programs consider how digital tools like CAD4TB can be integrated into screening and diagnosis strategies to improve early detection and treatment.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.29142734.v2（source: https://figshare.com/articles/dataset/Pulmonary_tuberculosis_prediction_using_CAD4TB_artificial_intelligence_computer-aided_detection_for_tuberculosis_based_on_thoracic_x-ray_photos_among_Indonesian_subjects_in_hospital_-_Data_for_Publication/29142734）。