估计依赖于个体化特征的个性化诊断规则数据集
基于帕金森病脑影像数据,研究个性化诊断规则以选择最优PET或DTI模态,提升疾病筛查精准性。

基本信息
资源简介
估计依赖于个体化特征的个性化诊断规则数据集
【一句话概览】
本数据集是 figshare 公开的影像数据集,收录 1 个文件、合计 17.79 KB,主题涵盖 Parkinson''s Disease、Personalized Diagnosis、Cancer Screening、Weighted Support Vector Machine、Statistics,可用于医学图像分割、检测与分类模型的训练与评测,CC0 许可开放获取。
【数据集背景】
本数据集源站标题为《Dataset for: Estimating Personalized Diagnostic Rules Depending on Individualized Characteristics》。配套论文《Estimating personalized diagnostic rules depending on individualized characteristics》发表于 Statistics in Medicine(2016),DOI:10.1002/sim.7182。源站首次发布:2017-03-29。
【数据内容】
源站原始描述:There is an increasing demand for personalization of disease screening based on assessment of patient risk and other characteristics. For example, in breast cancer screening, advanced imaging technologies have made it possible to move away from "one-size-fits-all" screening guidelines to targeted risk-based screening for those who are in need. Since diagnostic performance of various imaging modalities may vary across subjects, applying the most accurate modality to the patients who would benefit…
中文译文(机器翻译,仅供快速理解,请以原文为准):疾病筛查的个体化需求日益增加,这种个体化基于对患者风险及其他特征的评估。例如,在乳腺癌筛查中,先进成像技术已使人们有可能摆脱“一刀切”的筛查指南,转向针对有需要者的靶向、基于风险的筛查。由于不同成像方式的诊断性能可能因受试者而异,要将最准确的成像方式应用于获益最大的患者,就需要个体化策略。为满足这些需求,我们提出了新的机器学习方法,通过最大化受试者亚组间敏感度与特异度的加权组合,来估计用于医学筛查或诊断的个体化诊断规则。我们首先开发了可用于估计个体化诊断规则的方法,其中竞争的成像方式或筛查策略在同一受试者上被观测到(配对设计)。接下来,我们提出了用于并非所有受试者都接受两种成像方式的研究的方法(非配对设计)。我们研究了个体化诊断规则的理论性质,包括一致性和风险界,并进行了模拟研究以证明所提方法的有效性。最后,我们分析了来自帕金森病脑成像研究的数据,该研究使用正电子发射断层扫描(PET)或弥散张量成像(DTI)方式,并采用配对和非配对设计。我们的结果表明,在某些情况下,与“一刀切”的分配策略相比,估计出的个体化成像方式分配可改善经验AUC。
文件 pdr.bib 为文本内容,开头为:% This file was created with JabRef 2.10. % Encoding: MacRoman @article{aronszajn1950theory, title={Theory of reproducing kernels}, author={Aronszajn, Nach…
【数据结构与技术规格】
文件数 1 个,合计 17.79 KB。pdr.bib:text/plain,17.79 KB。数据集 DOI:10.6084/m9.figshare.4204935.v1。
【主题与分类】
源站学科分类:Statistics not elsewhere classified、Other biomedical and clinical sciences not elsewhere classified。主题标签:Parkinson''s Disease、Personalized Diagnosis、Cancer Screening、Weighted Support Vector Machine、Statistics、Medicine。
【适用方向】
影像类数据可用于医学图像分析模型(检测、分割、分类)的训练与评测,也可用于标注质量与成像参数相关性的研究。
【获取与许可】
源站页面:https://wiley.figshare.com/articles/dataset/Dataset_for_Estimating_Personalized_Diagnostic_Rules_Depending_on_Individualized_Characteristics/4204935
使用许可:CC0(https://creativecommons.org/publicdomain/zero/1.0/)。
规范引用:Liu, Ying; Wang, Yuanjia; Huang, Chaorui; Zeng, Donglin (2017). Dataset for: Estimating Personalized Diagnostic Rules Depending on Individualized Characteristics. Wiley. Dataset
【使用注意】
· 源站最后修改于 2023-06-02,引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载,适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档,适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务(收技术服务费,非数据销售)
暂未开放当前数据集主要来源为 Kaggle 公开托管,完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取(Figshare)
- 源站标题:Dataset for: Estimating Personalized Diagnostic Rules Depending on Individualized Characteristics
- DOI:10.6084/m9.figshare.4204935.v1
- 发布日期:2017-03-29
- 文件数:1 个
- 文件总体积:17.79 KB
- 源站页面:https://wiley.figshare.com/articles/dataset/Dataset_for_Estimating_Personalized_Diagnostic_Rules_Depending_on_Individualized_Characteristics/4204935
命令行下载
curl -L -o "pdr.bib" "https://ndownloader.figshare.com/files/6862140"
文件清单
pdr.bib(17.79 KB)
文件总体积 17.79 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
There is an increasing demand for personalization of disease screening based on assessment of patient risk and other characteristics. For example, in breast cancer screening, advanced imaging technologies have made it possible to move away from “one-size-fits-all” screening guidelines to targeted risk-based screening for those who are in need. Since diagnostic performance of various imaging modalities may vary across subjects, applying the most accurate modality to the patients who would benefit the most requires personalized strategy. To address these needs, we propose novel machine learning methods to estimate personalized diagnostic rules for medical screening or diagnosis by maximizing a weighted combination of sensitivity and specificity across subgroups of subjects. We first develop methods that can be applied to estimate personalized diagnostic rules where competing modalities or screening strategies are observed on the same subject (paired design). Next, we present methods for studies where not all subjects receive both modalities (unpaired design). We study theoretical properties including consistency and risk bound of the personalized diagnostic rules, and conduct simulation studies to demonstrate effectiveness of the proposed methods. Lastly, we analyze data collected from a brain imaging study of Parkinson’'s disease using positron emission tomography (PET) or diffusion tensor imaging (DTI) modalities with paired and unpaired designs. Our results show that in some cases a personalized modality assignment is estimated to improve empirical AUC compared to a “one-size-fits-all” assignment strategy.
许可
CC0
引用
学术使用请引用 DOI 10.6084/m9.figshare.4204935.v1(source: https://wiley.figshare.com/articles/dataset/Dataset_for_Estimating_Personalized_Diagnostic_Rules_Depending_on_Individualized_Characteristics/4204935)。
数据缺失?
依托陕西、四川两大基地,我们与超过十家三甲医院建立直接合作关系,覆盖合规授权、采集治理、专业标注、数据交付的全流程,为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务?立即联系我们获取专业方案。




