Updated Jan 15, 2021

CAD4TB: Artificial Intelligence software for tuberculosis detection

https://www.delft.care/cad4tb/

Delft Imaging

Send Message

CAD4TB (Computer Aided Detection for Tuberculosis) is an artificial intelligence software which analyses a digital chest X-ray image, and gives an indication if the subject on the image has active TB.

The CAD4TB software starts with a quick inspection of X-ray images. It normalizes the image to correct for input from various modalities, and then detects different abnormal structures that may be related to TB. The system has been trained in the detection of these abnormalities by applying deep learning to tends-of-thousands of normal and abnormal X-rays from over 15 countries. CAD4TB also rec...
SEE ALL
The CAD4TB software starts with a quick inspection of X-ray images. It normalizes the image to correct for input from various modalities, and then detects different abnormal structures that may be related to TB. The system has been trained in the detection of these abnormalities by applying deep learning to tends-of-thousands of normal and abnormal X-rays from over 15 countries. CAD4TB also received expert feedback from lung specialists, making it extremely accurate and reliable. Within 20 seconds, the CAD4TB software analyses a chest X-ray and shows the output as a score between 0 and 100, indicating the likelihood that the subject on the image has active TB. The score also includes a texture heat map overlaying the original X-ray image which indicates abnormalities. Only if the output score is higher than a certain threshold will the patient need a subsequent sputum test to finalize the diagnosis. This process brings down both the cost and the time-to-treatment.
SEE LESS

Stage 6: Sustained Scale

CAD4TB is CE-certified, validated through over 50 publications, implemented in 40 countries, and has screened over 6 million people for tuberculosis.

Focus Areas:

Infectious & Vector Diseases, Medical Devices, AI and 1 MoreSEE ALL

Infectious & Vector Diseases, Medical Devices, AI and HealthSEE LESS

Implemented In:

Zambia, South Africa, Papua New Guinea and 26 MoreSEE ALL

Zambia, South Africa, Papua New Guinea, Malawi, Romania, Nepal, Swaziland, Sudan, Congo, Democratic Republic of the, Nigeria, Namibia, Mozambique, Liberia, India, Sierra Leone, Myanmar, Pakistan, Brazil, Ethiopia, Eritrea, Botswana, Philippines, Peru, Lesotho, Ghana, Georgia, Cameroon, Kenya and UgandaSEE LESS

6,000,000
Lives Impacted to Date
1
Key Partner
29
Countries Implemented In
23
Employees

Problem

Most countries where TB is widespread are resource-constrained; its prevalence tends to be higher in countries with lower per-capita GDP. It is, therefore, not surprising that one of the main reasons TB incidences have not significantly decreased is the lack of simple, effective and inexpensive ways to detect new TB cases at an early stage. While the only way to diagnose TB is with tests, they are usually high-cost.

}

Solution

Delft Imaging has solved the TB detection challenge by combining low-cost, quick digital X-rays with deep learning and remote expertise. It’s called CAD4TB (Computer-Aided Detection for Tuberculosis). CAD4TB takes PA Chest X-ray as input, and produces abnormality score (0-100) and heatmap as output. if TB is likely present in a patient, a follow-up test such as GeneXpert can be administered. This way, a patient can be diagnosed and treated within one day. Subject age is 4 years or above.

Mission and Vision

Delft Imaging is a social enterprise and envisions a world in which everyone can benefit from the modern world advances in the field of healthcare. It is this belief that drives our mission to develop and deliver unique health innovations, particularly affordable, innovative diagnostic imaging devices, and e-health software that respond to the specific needs of vulnerable communities around the world. Delft Imaging has particularly been focusing on the screening for TB with CAD4TB.

Competitive Advantage

Delft’s innovative approach to screening and diagnosing tuberculosis has been supported by many of our colleagues in the scientific community. The in-depth evaluations of CAD4TB in scientific articles are available (https://www.delft.care/publications/).

The Team Behind the Innovation

Our in-house expertise ranges from software development, engineering to public health and international business developers. Altogether, this diverse range of expertise is what has allowed us to screen over 6 million people in 40 countries through our tuberculosis-focused projects. We wish to apply our market knowledge and expertise into other areas of point of care diagnostics in developing countries.

EXECUTIVE TEAM INCLUDES WOMEN

Milestone

Dec 2019
Lives Impacted
6,000,000
Jan 2019
New Country Implemented In
Ghana, Georgia, Cameroon, Kenya and Uganda
Jan 2015
Recognition ReceivedPENDING
Jan 2011
New Country Implemented In
Zambia and South Africa
Jan 2007
Key Partnership
Research
 
as part of
 First research project with CAD4TB

Supporting Materials

CAD4TB-7-Leaflet-orientation-null.pdf
CAD4TB-orientation-null.pdf