空间变系数不平等：评估患者特征对乳腺癌生存的影响如何随地理位置变化

数据集获取（Figshare）

• 源站标题：Spatially Varying Coefficient Inequalities: Evaluating How the Impact of Patient Characteristics on Breast Cancer Survival Varies by Location
• DOI：10.1371/journal.pone.0155086
• 发布日期：2016-05-05
• 文件数：5 个
• 文件总体积：5.39 MB
• 源站页面：https://plos.figshare.com/articles/dataset/Spatially_Varying_Coefficient_Inequalities_Evaluating_How_the_Impact_of_Patient_Characteristics_on_Breast_Cancer_Survival_Varies_by_Location/3306862

命令行下载

curl -L -o "S1 Fig.TIF" "https://ndownloader.figshare.com/files/5144830"
curl -L -o "S2 Fig.TIF" "https://ndownloader.figshare.com/files/5144839"
curl -L -o "S3 Fig.TIF" "https://ndownloader.figshare.com/files/5144848"
curl -L -o "S4 Fig.TIF" "https://ndownloader.figshare.com/files/5144860"
curl -L -o "S5 Fig.TIF" "https://ndownloader.figshare.com/files/5144869"

文件清单

• S1 Fig.TIF（1.01 MB）
• S2 Fig.TIF（1.60 MB）
• S3 Fig.TIF（877.06 KB）
• S4 Fig.TIF（947.66 KB）
• S5 Fig.TIF（955.28 KB）

文件总体积 5.39 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

An increasing number of studies have identified spatial differences in breast cancer survival. However little is known about whether the structure and dynamics of this spatial inequality are consistent across a region. This study aims to evaluate the spatially varying nature of predictors of spatial inequality in relative survival for women diagnosed with breast cancer across Queensland, Australia. All Queensland women aged less than 90 years diagnosed with invasive breast cancer from 1997 to 2007 and followed up to the end of 2008 were extracted from linked Queensland Cancer Registry and BreastScreen Queensland data. Bayesian relative survival models were fitted using various model structures (a spatial regression model, a varying coefficient model and a finite mixture of regressions model) to evaluate the relative excess risk of breast cancer, with the use of Markov chain Monte Carlo computation. The spatially varying coefficient models revealed that some covariate effects may not be constant across the geographic regions of the study. The overall spatial patterns showed lower survival among women living in more remote areas, and higher survival among the urbanised south-east corner. Notwithstanding this, the spatial survival pattern for younger women contrasted with that for older women as well as single women. This complex spatial interplay may be indicative of different factors impacting on survival patterns for these women.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0155086（source: https://plos.figshare.com/articles/dataset/Spatially_Varying_Coefficient_Inequalities_Evaluating_How_the_Impact_of_Patient_Characteristics_on_Breast_Cancer_Survival_Varies_by_Location/3306862）。