低剂量CT用于肺癌筛查的系统评价总体回顾

数据集获取（Figshare）

• 源站标题：An umbrella review of systematic evidence on the Low Dose Computed Tomography (LDCT) for lung cancer screening
• DOI：10.6084/m9.figshare.29571965.v1
• 发布日期：2025-07-15
• 文件数：2 个
• 文件总体积：9.58 MB
• 源站页面：https://tandf.figshare.com/articles/dataset/An_umbrella_review_of_systematic_evidence_on_the_Low_Dose_Computed_Tomography_LDCT_for_lung_cancer_screening/29571965

命令行下载

curl -L -o "ifon_a_2531428_sm7976.docx" "https://ndownloader.figshare.com/files/56286914"
curl -L -o "ifon_a_2531428_sm7974.docx" "https://ndownloader.figshare.com/files/56286917"

文件清单

• ifon_a_2531428_sm7976.docx（9.55 MB）
• ifon_a_2531428_sm7974.docx（22.57 KB）

文件总体积 9.58 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

Despite lung cancer’s high mortality rate, many countries still lack organized lung cancer screening programs. This review aims to evaluate the impact of low-dose computed tomography (LDCT) screening on lung cancer diagnosis, mortality, and overall clinical outcomes.
Following the Joanna Briggs Institute methodology for umbrella reviews, a comprehensive search was conducted in PubMed, Embase, and the Cochrane Library for reviews published between January 2013 and December 2023. Eligible meta-analyses included studies comparing LDCT screening with chest X-ray (CXR) or no screening, reporting outcomes such as sensitivity, specificity, and lung cancer mortality. The methodological quality of the included reviews was assessed using AMSTAR-2.
Out of 801 citations, 14 meta-analyses met the inclusion criteria. LDCT demonstrated high sensitivity (0.97, 95% CI: 0.94–0.98) and specificity (0.87, 95% CI: 0.82–0.91). It significantly increased early-stage lung cancer detection (RR: 1.31, 95% CI: 1.18–1.45) and reduced lung cancer mortality by 18% (RR: 0.82, 95% CI: 0.75–0.90). However, the reduction in all-cause mortality (RR: 0.91, 95% CI: 0.75–1.06) was not statistically significant. Overdiagnosis and false positives remain essential challenges.
This umbrella review confirms that LDCT screening effectively reduces lung cancer mortality, particularly in high-risk populations.
Lung cancer was the most commonly diagnosed cancer worldwide in 2022, leading to over 2.5 million new cases and 1.8 million deaths. Although lung cancer has a high death rate, many countries still do not have screening programs in place to detect it early. This review examined the effectiveness of a special type of scan, known as low-dose computed tomography (LDCT), in detecting lung cancer early and saving lives. Researchers searched several major medical databases for studies published between 2013 and 2023. They focused on studies that compared LDCT scans with regular chest X-rays or no screening and checked the quality of the studies they included. Out of 801 studies found, 14 high-quality reviews were selected. The results showed that LDCT scans are very good at correctly detecting lung cance

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.29571965.v1（source: https://tandf.figshare.com/articles/dataset/An_umbrella_review_of_systematic_evidence_on_the_Low_Dose_Computed_Tomography_LDCT_for_lung_cancer_screening/29571965）。