患者特征

数据集获取（Figshare）

• 源站标题：Patients’ characteristics.
• DOI：10.1371/journal.pone.0322102.t002
• 发布日期：2025-06-04
• 文件数：1 个
• 文件总体积：9.73 KB
• 源站页面：https://plos.figshare.com/articles/dataset/Patients_characteristics_/29238607

命令行下载

curl -L -o "Table 2.xls" "https://ndownloader.figshare.com/files/55122571"

文件清单

• Table 2.xls（9.73 KB）

文件总体积 9.73 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

Background and aims
Chronic liver disease (CLD) represents a significant global health challenge necessitating the evaluation of liver fibrosis. This study aimed to evaluate the diagnostic performance of microvascular flow (MV-flow) imaging in evaluating liver fibrosis and compare it with other non-invasive tools.
Methods
Between July 2020 and June 2022, we prospectively enrolled patients scheduled for liver biopsy, concurrently measuring MV-flow imaging, transient elastography (TE), and two-dimensional shear wave elastography (2D-SWE) as part of the assessment process. We evaluated the diagnostic performance of MV-flow imaging, 2D-SWE, and TE based on histologic staging of liver fibrosis using the area under the receiver operating characteristic curve (AUROC), and calculated the optimal cut-off value.
Results
A total of 89 participants were included. Non-alcoholic fatty liver disease was the most common etiology of CLD (32.6%). The liver fibrosis stage distribution was as follows: stage 0 (11.2%), stage 1 (31.5%), stage 2 (25.8%), stage 3 (13.5%), and stage 4 (18.0%). The MV-flow scoring system’s cut-off values and AUROCs for predicting stage 2, stage 3, and cirrhosis were 2.1 (0.836), 2.5 (0.955), and 2.9 (0.942), respectively. The MV-flow scoring system’s performance in predicting advanced fibrosis (stage 3) was comparable to TE (p = 0.170) and 2D-SWE (p = 0.456). MV-flow imaging misclassified 9.0% of patients in predicting advanced fibrosis. A sequential combination of 2D-SWE and MV-flow imaging, following the specified cut-off, minimized the risk of missing advanced fibrosis to 1.2%.
Conclusion
MV-flow imaging is an effective tool for predicting liver fibrosis stage. Integrating MV-flow imaging with 2D-SWE can enhance the assessment of liver fibrosis in patients with CLD.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0322102.t002（source: https://plos.figshare.com/articles/dataset/Patients_characteristics_/29238607）。