肺清除指数评估

研究关注学龄前儿童,主要目的是评估初次访视时 LCI 与胸部低剂量 CT 终点之间的相关性,次要目的包括评估 LCI 与各次访视呼吸功能测量值的相关性、LCI 与呼吸功能终点及 CT 演变的相关性,以及 LCI 对两年后呼吸功能的预测价值

Assistance Publique - Hôpitaux de ParisAssistance Publique - Hôpitaux de Paris
clinicaltrials
浏览 8
医学影像回归Cystic Fibrosis
Evaluation of the Lung Clearance Index

基本信息

模态
医学影像
任务类型
回归
创建/更新时间
2026-10-12

资源简介

肺清除指数评估

本数据集来自 clinicaltrials.gov,主题为囊性纤维化(Cystic Fibrosis)患儿中肺清除指数(LCI)的评估。研究关注学龄前儿童,主要目的是评估初次访视时 LCI 与胸部低剂量 CT 终点之间的相关性,次要目的包括评估 LCI 与各次访视呼吸功能测量值的相关性、LCI 与呼吸功能终点及 CT 演变的相关性,以及 LCI 对两年后呼吸功能的预测价值。数据可用于呼吸系统疾病中影像与功能指标关联分析及预测建模(来源 clinicaltrials.gov)。

【数据内容】

源站描述(机器翻译,仅供参考):疾病:囊性纤维化。对于患有囊性纤维化(CF)的幼儿,必须尽早发现肺部 CF 病变,以启动积极治疗,限制不可逆病变。肺清除指数(LCI)评估肺泡容积中的气体清除,是一种在学龄前儿童中易于实施的技术。主要目的:评估初次访视时 LCI 与胸部低剂量计算机体层摄影(CT)终点之间的相关性。次要目的:1. 评估每次访视时 LCI 与呼吸功能测量值之间的相关性;2. 仅针对两年后由其转诊医生要求进行胸部低剂量 CT 的儿童,评估 LCI 的演变与呼吸功能终点及 CT 演变之间的相关性;3. 评估 LCI 对学龄前儿童两年后呼吸功能的预测价值。这是一项前瞻性 m

【主题与分类】

主题标签:Cystic Fibrosis。本站分类:呼吸系统疾病。

【获取与许可】

源站页面:https://clinicaltrials.gov/study/NCT02342951

官方服务

专家保障全链路合规授权与标注交付

陕川双基地 × 超十家三甲医院直连

从合规授权、采集治理、专业标注到数据集交付,我们提供全链路闭环服务,让高质量临床数据即拿即用。

⚡️ 需要原始数据或标注支持?联系我们获取定制方案。

帮我联系

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

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。

免费样本无法满足模型训练要求?千方提供经三甲医院脱敏、带病理回证与专家标注的商业级专病数据集。

使用方式

数据集获取

源站:https://clinicaltrials.gov/study/NCT02342951

标准获取流程:

  1. 访问源站链接,注册/登录账号;
  2. 进入数据集详情页,按页面指引申请权限或直接下载;
  3. 部分平台提供 SDK,例如:
    • OpenDataLab: pip install openxlab 后 openxlab.dataset.get(...)
    • ModelScope: pip install modelscope 后 modelscope download
    • 天池: 登录后页面提供直链下载
      以源站「数据下载/使用文档」页面为准。

数据说明

Conditions: Cystic Fibrosis. It is mandatory to detect as early as possible lung CF disease in the young child with CF to initiate active therapies limiting irreversible lesions. Lung Clearance Index (LCI) which evaluates gas clearance from the alveolar volume is an easy to-do technique in pre-school children. Main objective To evaluate correlation between LCI and thoracic low dose computed tomodensitometry (CT) endpoints at initial visit Secondary objectives 1. To evaluate correlation between LCI and respiratory function measurements at each visit 2. To evaluate correlation between the evolution of LCI and respiratory function endpoints and the evolution of CT only for the children for whom a thoracic low dose CT is requested by their referent doctor after two years. 3. To evaluate LCI predictive value for respiratory function 2 years later in preschool children. This is a prospective multicenter cohort study. Study visits will be performed each year during the annual check up for normal follow up of the child. Initial visit (Visit 1) takes place during an annual check-up during which a low dose CT was prescribed. It will include following tests: LCI, Lung function tests (LFTs) performed according to age (forced volumes and flows, plethysmographic specific airway resistances and interrupter resistances), and a low dose CT scan performed according a standardized protocol. Visit 2 will be performed 12 ± 3 months later and will include following tests: LCI , LFTs. Visit 3 will be performed 24 ± 3 months later and will include following tests: LCI , LFTs and, if judged necessary by the child’s referent doctor, a low dose CT scan performed according to a standardized protocol. Anthropometric data, infection history, treatment will be collected at each visit. Recruiting period: 1 year Study period: 2 years per patient, 3 years as a whole LCI will help to evaluate early ventilation inhomogeneity due to small bronchi abnormalities in young children with CF. Concordance between LCI and CT endpoints eva

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。

需要用于商业化训练或医疗器械注册(NMPA/FDA)?

公开数据往往缺乏完整的病理回证与专家标注。千方医数集依托陕川双基地与超十家三甲医院直连,提供完全合规、去标识化、支持注册级质控的专病数据集交易服务。