Our CAD4TB solution
To detect tuberculosis-related abnormalities in posterior anterior chest X-rays, Thirona developed CAD4TB™.This computer-aided detection software takes a single chest X-ray as its input, in the form of a DICOM image, and produces several outputs: a quality assessment of the input image, a heat map highlighting possible abnormal areas, and a score between 0 and 100 indicating the likelihood of the X-ray being abnormal and the subject on the X-ray being affected by tuberculosis.
How it works
CAD4TB™ has been developed following the principles of deep learning: in the process of computing the score, it compares regions in the input image with regions extracted from normal and abnormal images previously processed by the system, which constitute the so-called training set. One of the conditions for proper supervised learning is that this training set should be representative of the test data; otherwise, results may not be reliable. To fulfill this condition, and thus make CAD4TB™ applicable to diverse scenarios, the system has been trained with data from several populations and several X-ray devices.
More on CAD4TB
Our CAD4COVID solution
Nearly all countries around the world are facing COVID-19. This crisis is inspiring unprecedented global efforts across all industries, and we are glad to offer our support. Together with Delft Imaging, we developed CAD4COVID: an artificial intelligence software that triages COVID-19 suspects on chest X-rays images.
CAD4COVID has been developed with the intention to support triaging in resource-constrained settings and high-prevalence areas. It will become available in the week of March 30th and will be free-of-charge.
COVID-19 is a global health crisis that will long be remembered and that has impacted the lives of millions of people around the world. Both low- and high-resource countries have been greatly impacted by this public health crisis. In response to this crisis, we want to support Ministries of Health and healthcare facilities around the world by leveraging our extensive experience in artificial intelligence and tuberculosis screening, with which we have already screened millions of people around the world.
The ingenuity behind CAD4COVID uses the same technical core as our proven software for tuberculosis detection, CAD4TB. CAD4TB is a significant part of the equation because CAD4COVID was built upon the same high-quality standard as CAD4TB, which is validated by over 40 academic publications and has contributed to screening 6 million people worldwide across 40 countries.
How it works
CAD4COVID will generate a score between 0 and 100 indicating the extent of COVID-19 related abnormalities, display such lung abnormalities through a heatmap and quantify the percentage of the lung that is affected.
CAD4COVID can be accessed by filling out the form at the bottom of this page: https://www.delft.care/cad4covid/
When this is done, you will be given access through a CAD4COVID account that will be created for your facility. Fill in the form to access CAD4COVID or if you want to ask us any questions.
CAD4TB is a CE certified product. The CAD4COVID module has been developed in support of the crisis situation. It is not a certified product. It is not intended for diagnostic purposes and only for research. Delft Imaging nor Thirona can be made liable for its use.
Continuously improved and optimized
CAD4COVID will be updated and optimized on a continuous basis. For this reason, we welcome any support that can be provided. By using CAD4COVID, your data will be processed for the purpose of analysing the COVID-19 cases. It will not be used for product development purposes unless explicit approval is given by your facility. However, organizations that are able to share CXR’s of COVID-19 cases will receive first access to the tool as it will result in a further optimized solution for everyone.
Your data will be processed safely and securely
Thirona and Delft Imaging adhere to the European GDPR regulations. Any data processed through CAD4COVID will be done safely and securely. Your data will not be used for product development purposes unless given explicit approval.