Skip to content

vbookshelf/List-of-TB-and-Pneumonia-Datasets

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

90 Commits
 
 
 
 

Repository files navigation

List of TB and Pneumonia Chest X-ray Datasets

A list of publicly available Tuberculosis (TB) and Pneumonia chest x-ray datasets.

Last Updated: 3 March 2023


An image from the TBX11K dataset

TB and Pneumonia indicators look similar on chest x-rays. That's why I decided to include datasets for both diseases in this list.

In some cases the entire dataset is dedicated to one disease. In other cases the TB or Pneumonia images are located inside other much larger datasets. Some datasets include bounding boxes that can be used to train detection models. The image quantities are appoximate.


Tuberculosis (TB) Datasets

Shenzhen and Montgomery datasets

TBX11K Simplified

Belarus dataset

DA and DB datasets

VinDr-PCXR dataset

VinDr-CXR dataset

Tuberculosis (TB) Chest X-ray Database

NIAID TB dataset

PadChest dataset


Pneumonia Datasets

Child Chest X-Ray Images (Version 2)

Child Chest X-Ray Images (Version 3)

RSNA Pneumonia Detection Challenge


The datasets that follow are multi label datasets that contain pneumonia images.
I've listed the approx. number of pneumonia images in each.

VinDr-PCXR dataset

VinDr-CXR dataset

CheXpert Dataset

MIMIC-CXR Database

NIH ChestX-ray14 dataset

Open-i Chest X-ray images

PadChest dataset

Large Dataset of OCT and Chest X-Ray Images (Version 3)


Helpful Resources

Kaggle COVID-19 Comp solutions

This is a link to short video summaries of the top 10 solutions of the Kaggle COVID-19 AI Detection Challenge (2021).
Includes links to the solution writeups and code.
Many of the winning models were pre-trained on the datasets listed above.
https://www.rsna.org/education/ai-resources-and-training/ai-image-challenge/covid-19-al-detection-challenge-2021


ChatGPT - A virtual domain specialist

https://openai.com/blog/chatgpt/
Do you sometimes wish that you could consult with a radiologist when training your models? I'm finding that ChatGPT is the next best thing. In fact ChatGPT has passed the three-part medical exam that doctors take in order to practice medicine in the US.

This is the answer I got when I asked, "How do radiologists differentiate between TB and Pneumonia?"

"""

Radiologists can differentiate pneumonia from tuberculosis (TB) on chest x-rays by looking for specific characteristics in the images. Here are some of the ways they might differentiate between the two conditions:

  1. Location: Pneumonia typically affects one lobe of the lung, while TB can involve multiple lobes.
  2. Shape: The opacities caused by pneumonia are often round or lobular, while the opacities caused by TB are often more irregular in shape.
  3. Size: The opacities caused by pneumonia are typically smaller than those caused by TB.
  4. Distribution: Pneumonia is more likely to affect the peripheral parts of the lung, while TB is more likely to affect the central portions of the lung.
  5. Associated findings: Pneumonia can cause pleural effusion (fluid in the pleural cavity), while TB often causes small nodules or cavities.

Radiologists will also consider the patient's medical history, such as recent exposure to infectious agents, symptoms, and other test results, in making their diagnosis. In some cases, additional tests, such as sputum analysis or blood tests, may be needed to confirm the diagnosis and differentiate between pneumonia and TB.

"""

Please keep in mind that ChatGPT makes mistakes - the facts are not always correct.
It's free to use.


About

A list of publicly available Tuberculosis (TB) and Pneumonia chest x-ray datasets.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published