肺非结核分枝杆菌感染中咳出痰、诱导痰与咽拭子用于培养、AFB涂片及细胞因子的比较

数据集获取

源站：https://clinicaltrials.gov/study/NCT01150721

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: Mycobacterium Infections, Non-tuberculous. In this protocol, a repeated measure design is used to examine microbial and molecular results in subjects with a diagnosis of pulmonary nontuberculous mycobacterial infection. Patients often experience difficulties in the spontaneous expectoration of sputum free from contamination with oral flora which contributes to the poor quality of some respiratory specimens sent to the laboratory. At present, it is not known how induced sputum, expectorated sputum, and pharyngeal swabs compare for acid fast bacilli (AFB) smear and culture results. Appropriate specimens are needed in the clinical setting for optimum diagnosis. In this study, procedures for the non-invasive collection of respiratory secretions will be used to decrease risk of specimen contamination. Subjects who cannot produce respiratory secretions will be compared to patients who are successful. It is not known which factors prevent production of respiratory secretions for testing. Airway inflammation may contribute to difficulty in producing sputum along with dyspnea, phase of illness (newly diagnosed or chronic infection), treatment status, and respiratory condition severity. Subjects will be characterized by phase of illness determined by health history and inflammation using common laboratory tests of inflammation. Respiratory specimens and blood will be collected for microbial testing and a portion will be stored then tested for analysis of pro-inflammatory cytokines (IL-1, IL-6, IL-8, TNF-alpha, & IFN-gamma). Clinical, demographic, laboratory, and patient subjective variables will be tested using regression statistical methods to determine predictors for specimen production success. Clinical variables to be tested include forced expiratory volume at one minute (FEV1) from a pulmonary function test (PFT), phase of illness and treatment, and age. The laboratory tests indicating inflammation include erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), and Beta-2-Microglobulin (Beta-2M). Patient

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。