Pulmonary Chest X-Ray Abnormalities

Home » Dataset Download » Pulmonary Chest X-Ray Abnormalities

Pulmonary Chest X-Ray Abnormalities

Datasets

File

Pulmonary Chest X-Ray Abnormalities

Use Case

Computer Vision

Description

Tuberculosis is a disease that affects many people in developing countries. While treatment is possible, it requires an accurate diagnosis first.

About Dataset

Content and context

In countries where tuberculosis is common, many people struggle to get the right diagnosis because there aren’t enough experts to read X-ray images accurately. Even though there are X-ray machines available, there’s a lack of trained professionals to interpret the images. But imagine if there was a computer program that could quickly and affordably analyze these X-rays, helping doctors spot tuberculosis more easily. This could make a big difference in diagnosing and treating the disease.

In countries where people move frequently or apply for work permits, they often need X-ray scans as part of their health checks. Right now, doctors have to look at each X-ray picture one by one, which takes a lot of time. But what if there was a computer program that could do this job faster and better?

It could help doctors make decisions more quickly and accurately, which could save time and money for everyone involved.

Acknowledgements

The two datasets were published together in an analysis here: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4256233/.
The datasets come from Shenzhen and Montgomery respectively.

China Set – The Shenzhen set – Chest X-ray Database

The main collection of digital images for Tuberculosis comes from a partnership between the National Library of Medicine in Maryland, USA, and Shenzhen No.3 People’s Hospital, linked with Guangdong Medical College in Shenzhen, China. These X-rays are taken in clinics where patients don’t stay overnight and are captured using Philips DR Digital Diagnose systems as part of their regular check-ups.
Number of X-rays:

336 cases with manifestation of tuberculosis, and
326 normal cases.

Scientists who use this dataset are requested to give credit to where the data came from. This includes the National Library of Medicine and National Institutes of Health in Bethesda, MD, USA, and the Shenzhen No.3 People’s Hospital, which is linked with Guangdong Medical College in Shenzhen, China. Also, they should mention and cite the following publications:

Jaeger S, Karargyris A, Candemir S, Folio L, Siegelman J, Callaghan F, Xue Z, Palaniappan K, Singh RK, Antani S, Thoma G, Wang YX, Lu PX, McDonald CJ. Automatic tuberculosis screening using chest radiographs. IEEE Transactions on Medical Imaging. 2014 Feb;33(2):233-45. doi: 10.1109/TMI.2013.2284099. PMID: 24108713

Candemir S, Jaeger S, Palaniappan K, Musco JP, Singh RK, Xue Z, Karargyris A, Antani S, Thoma G, McDonald CJ. Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Transactions on Medical Imaging. 2014 Feb;33(2):577-90. doi: 10.1109/TMI.2013.2290491. PMID: 24239990

Montgomery County X-ray Set

The X-ray pictures in this collection are from the tuberculosis control program managed by the Department of Health and Human Services in Montgomery County, MD, USA. There are a total of 138 X-rays taken from the back to the front of the chest (posterior-anterior). Among these, 80 are normal, while 58 show signs of tuberculosis. These images don’t have any personal information and are saved in a DICOM format, which is a common medical image format. This dataset covers various abnormalities, like fluid buildup and small spots called miliary patterns. Additionally, there’s a separate text file containing the readings by radiologists.

Ideas

Experiment with lung segmentation
Build disease classifiers for various conditions
Test models on data across different manufacturers

Contact Us

Let's Discuss your Data collection Requirement With Us

To get a detailed estimation of requirements please reach us.

Pulmonary Chest X-Ray Abnormalities