COVID-19图像数据集
COVID-19胸部X光和CT图像数据集，包含阳性和疑似病例以及其它肺炎图像，用于诊断研究。
基本信息
资源简介
该数据集包含COVID-19阳性或疑似患者的胸部X光和CT图像，以及其他病毒性和细菌性肺炎的图像，用于COVID-19诊断和相关研究。
下载信息
注册下载
Tips: 该数据集需要在对应的数据源网站注册通过后，才能进行数据下载，注册有对应要求，或者需要收费。
暂未开放公开下载
Tips: 该数据集属于公开下载，应该可以免费公开下载。
免登录有偿下载
Tips: 该数据集 Qianfanghub 可以协助提供有偿下载服务，注意，服务不针对数据相关产权，只是技术服务费。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放千方医数集，医疗数据集部分，是为社区服务的公开医疗数据集搜索引擎，并不存储或者下载原始的任何数据。 如果您有其他医疗数据需求，可以和客服联系，或者下工单。我们有强大的三甲医疗机构帮助您提供个性化的医疗数据定制、采集、标注服务。
使用方式
数据集获取
git clone https://github.com/bganglia/covid-chestxray-dataset.git
curl -L -o repo.zip https://github.com/bganglia/covid-chestxray-dataset/archive/refs/heads/master.zip
unzip repo.zip
源站 README 摘录（使用方式）
🛑 Note: please do not claim diagnostic performance of a model without a clinical study! This is not a kaggle competition dataset. Please read this paper about evaluation issues: https://arxiv.org/abs/2004.12823 and https://arxiv.org/abs/2004.05405
COVID-19 image data collection (🎬 video about the project)
Project Summary: To build a public open dataset of chest X-ray and CT images of patients which are positive or suspected of COVID-19 or other viral and bacterial pneumonias (MERS, SARS, and ARDS.). Data will be collected from public sources as well as through indirect collection from hospitals and physicians. All images and data will be released publicly in this GitHub repo.
This project is approved by the University of Montreal’'s Ethics Committee #CERSES-20-058-D
View current images and metadata
Current stats of PA, AP, and AP Supine views. Labels 0=No or 1=Yes. Data loader is here
COVID19_Dataset num_samples=408 views=[''PA'', ''AP'']
{''ARDS'': {0.0: 393, 1.0: 15},
''Bacterial Pneumonia'': {0.0: 379, 1.0: 29},
''COVID-19'': {0.0: 96, 1.0: 312},
''Chlamydophila'': {0.0: 407, 1.0: 1},
''Fungal Pneumonia'': {0.0: 395, 1.0: 13},
''Influenza'': {0.0: 407, 1.0: 1},
''Klebsiella'': {0.0: 401, 1.0: 7},
''Legionella'': {0.0: 404, 1.0: 4},
''Lipoid'': {0.0: 405, 1.0: 3},
''MERS'': {0.0: 408},
''Mycoplasma'': {0.0: 404, 1.0: 4},
''No Finding'': {0.0: 393, 1.0: 15},
''Pneumocystis'': {0.0: 395, 1.0: 13},
''Pneumonia'': {0.0: 17, 1.0: 391},
''SARS'': {0.0: 392, 1.0: 16},
''Streptococcus'': {0.0: 395, 1.0: 13},
''Varicella'': {0.0: 404, 1.0: 4},
''Viral Pneumonia'': {0.0: 75, 1.0: 333}}
COVID19_Dataset num_samples=134 views=[''AP Supine'']
{''ARDS'': {0.0: 133, 1.0: 1},
''Bacterial Pneumonia'': {0.0: 134},
''COVID-19'': {0.0: 12, 1.0: 122},
''Chlamydophila'': {0.0: 134},
''Fungal Pneumonia'': {0.0: 134},
''Influenza'': {0.0: 134},
''Klebsiella'': {0.0: 134},
''Legionella'': {0.0: 134},
''Lipoid'': {0.0: 134},
''MERS'': {0.0: 134},
''Mycoplasma'': {0.0: 134},
## 数据加载示例（图像类）
```python
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。
精度瓶颈？数据缺失？
当前公开数据无法满足您的算法精度？千方提供针对 新冠病毒感染 的高质量、多模态真实临床数据定制解决方案。
