CAD4TB Print

The University of Utrecht developed the Computer Aided Diagnosis tool in close cooperation with Rogan, University of Stellenbosch, Zambia AIDS related Tuberculosis Project (Zambart) and the Lung Institute of Cape Town. The UNION is involved in CAD4TB project progress updates and in the chest image database management. Partial financing for this scientific project was obtained from the Dutch Ministry of Economic Affairs with support from CheckTB!.

Computer Aided Diagnosis will enable automated accurate pre-screening on site by the digital X-ray system allowing radiologists or pulmonologists to focus more on analysing the TB suspect images. In addition CAD4TB will contribute to fewer "over-reading" by less experienced radiographers. This in combination with forwarding images for 2nd reading over low bandwidth mobile phone networks or the internet will revolutionise screening and early case detection in especially countries coping with limited resources, isolated health centres, risk groups and/or high co-infection with HIV.

Basis for the revolution in diagnostics

In 2004, the Image Science Institute of the Medical Centre of Utrecht University and Rogan (both of the Netherlands) prepared a prototype software protocol able to recognise TB in a database of 500 images with a sensitivity of 85% and a specificity of 50%.

The digital image can soon be interpreted on the spot within seconds by the CAD4TB protocol programmed to recognise image patterns consistent with TB. So digital Chest images can be stored and read on the spot in real time by the protocol, by the radiographer on a monitor or sent by mobile phone or internet to any venue for diagnosis by a distant radiologist.

These are exciting new developments in boosting TB case detection using CXR and are supported by many institutions in Africa and leading TB organizations in the World like the UNION, WHO and the Dutch KNCV TB Foundation.

 

The progress!

The “Computer Aided Diagnosis for TB (CAD4TB)” project is in full development. The Image Sciences Institute and Rogan collaborate with the University of Cape Town and the Desmond Tutu Lung Institute of the University of Stellenbosch (both of South Africa) and Zambart (Zambia) to develop and scientifically proof this breakthrough diagnostic capability.

In order to achieve this, tens of thousands of images will be analysed in the same systematic way and various advanced pattern recognition techniques are applied. While many of these images will be of healthy persons, a significant portion will come from TB patients that have also been diagnosed by culture, smear microscopy, clinical and other diagnostic methods.

The UNION will permanently be informed on developments in the study. At the 40th World Conference of the UNION in Cancun the CAD4TB prototype was presented to various stakeholders like NTPs, NGOs, KNCV TB Foundation, WHO, UNION and FIND.

Expected Outcome

The objective of the joint research is to achieve a computered TB screening capability with a sensitivity of > 90% and a specificity of > 80%. The specificity target will be the biggest challenge for the scientists. It is expected that on the basis of reading thousands of images (including access to patient information like HIV status), that patterns consistent with TB typical for co-infected patients will be found. This will further enhance the role of X-ray to effectively detect TB suspects  in people living with HIV.

CAD improves TB screening and supports active case finding by:

A high percentage of TB cases is identified easily wherever the digital camera is used.
    - Supporting radiographers and/or clinical officers with first and immediate electronic image reading;
    - Reducing number of human image interpretations;
    - Providing a powerful tool in prevalence studies;
    - Offering an effective quality assessment tool for health workers and NTP;
    - Cutting screening and diagnostics costs.
    (and will become available with Odelca-DR and other similar direct digital X-ray systems in 2010)
The reference images (including data on smear microscopy and culture) available in the database will support radiographers to interpret Chest images on the spot with higher accuracy.
Only a limited number of complex Chest images will require external radiological expertise.

While developed for TB, this system can be enhanced in the future to spot other lung diseases as well. It is thus expected to contribute to a broad Healthcare strengthening impact in an area where this is most needed.

Depending on the number of images tested, a Beta version of the new software is expected to be available early 2010. The full fledged version is due in 2010. The official release is planned for the second half of 2010.


 
 

Can your organization participate  in the study?

As TB manifests itself in different forms in people of different regional and ethnic backgrounds, it would be highly recommendable that the research includes images from different countries. If your organization would want to participate and patient privacy rules would allow this, then please contact This e-mail address is being protected from spambots. You need JavaScript enabled to view it   This e-mail address is being protected from spambots. You need JavaScript enabled to view it for further information.