表1_一种整合胶原蛋白特性、影像组学和临床数据预测胃癌预后的新型组合模型

数据集获取（Figshare）

• 源站标题：Table 1_A novel combined model integrating collagen properties, radiomics and clinical data to predict gastric cancer prognosis.docx
• DOI：10.3389/fonc.2026.1801350.s003
• 发布日期：2026-04-10
• 文件数：1 个
• 文件总体积：56.41 KB
• 源站页面：https://frontiersin.figshare.com/articles/dataset/Table_1_A_novel_combined_model_integrating_collagen_properties_radiomics_and_clinical_data_to_predict_gastric_cancer_prognosis_docx/31977591

命令行下载

curl -L -o "Table 1_A novel combined model integrating collagen properties, radiomics and clinical data to predict gastric cancer prognosis.docx" "https://ndownloader.figshare.com/files/63608286"

文件清单

• Table 1_A novel combined model integrating collagen properties, radiomics and clinical data to predict gastric cancer prognosis.docx（56.41 KB）

文件总体积 56.41 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

IntroductionGastric cancer (GC) is one of the most common malignant tumors in the world, and there is still no good method to predict the prognosis of GC patients. Collagens are the major component of the extracellular matrix (ECM), and abnormalities in collagen are closely associated with the development of GC.
MethodsThis study investigated collagen signatures in GC using bioinformatics analysis and picrosirius red staining. A total of 196 GC patients were included, with 138 assigned to the training group and 58 to the validation group. Multivariate analysis was performed to evaluate prognostic factors, and a predictive model was constructed by integrating collagen properties, radiomics, and clinical data.
ResultsThe study revealed that collagen signatures were associated with GC initiation and progression. Multivariate analysis confirmed that the picrosirius red risk score (HR = 1.1, 95% CI: 1.02–1.18, p = 0.013) and Radscore (HR = 2.34, 95% CI: 1.3–4.21, p = 0.005) were independent prognostic factors for overall survival. The combined model demonstrated high accuracy, with a C-index of 0.9 in the training group and 0.84 in the validation group, along with good goodness of fit and net benefit.
DiscussionThese findings suggest that a prognostic model integrating multiple types of data, including collagen characteristics, radiomics, and clinical factors, can better predict the overall survival of GC patients.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.3389/fonc.2026.1801350.s003（source: https://frontiersin.figshare.com/articles/dataset/Table_1_A_novel_combined_model_integrating_collagen_properties_radiomics_and_clinical_data_to_predict_gastric_cancer_prognosis_docx/31977591）。