Triage for COVID-19 Using Artificial Intelligence on Chest X-rays 

Delft Imaging is specialised in tuberculosis (TB) screening and with its proven CAD4TB solution has screened over 6 million people in 40 countries. We optimised CAD4TB to triage COVID-19 suspects and are launching this solution free-of-charge.

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. We developed CAD4COVID:  an artificial intelligence software that triages COVID-19 suspects on chest X-rays images and indicates the affected lung tissue.

CAD4COVID has been developed with the intention to support triaging in resource-constrained settings and high-prevalence areas. It has become available in the week of March 30th and its use 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.

CAD4COVID is the first AI software that is proved to perform at the same level as human expert readers to detect COVID-19 related abnormalities on chest X-ray images.
Read the study published in the Radiology journal. 

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.

Why CAD4COVID?

  • Made for resource-constrained settings and high-prevalence areas
  • Available free-of-charge in support of the COVID-19 crisis
  • CAD4COVID performs at the same level as human readers
  • Developed by companies with extensive experience in
    artificial intelligence for medical image analysis
  • Built on experience in detecting tuberculosis in over 40 countries
  • CAD4COVID will be continuously improved and optimized

CAD4COVID-CT

Besides CAD4COVID, CAD4COVID-CT has been launched by our partner Thirona. This software uses artificial intelligence for the analysis of COVID-19 on CT scans. The software assesses the suspicion of COVID-19 as well as the severity of the infection based on the percentage of affected lung. CAD4COVID has been made available globally and free-of-charge in support of the current crisis situation.

For more information and how to access CAD4COVID-CT, please go to: https://thirona.eu/cad4covid/ 

How can you access CAD4COVID?

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.

Liability clause
CAD4TB is a CE certified product. The CADCOVID module has been developed in support of the crisis situation. It is not a certified product. Notification of its use has been submitted to the Dutch Ministry of Health (IGJ). Note that the user assumes all responsibility and risk for the use of CAD4COVID. Under no circumstances shall Delft Imaging, its contributors/employees or its affiliated organizations or its employees or anyone else involved in developing or maintaining CAD4COVID be liable for any direct, indirect, incidental, special or consequential damages, or profit loss that result directly or indirectly from the use or inability to use the CAD4COVID AI software – or that result directly or indirectly from mistakes, omissions, interruptions, deletion of files, viruses, errors, defects, or any failure of performance or unauthorized access.

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.

I have read, acknowledge and understand the liability clause mentioned to the left of this form.
I understand that Delft Imaging prioritises organizations that are willing to share data to contribute to the improvement of the solution.

Today, we launch CAD4COVID, our free-of-charge solution that uses artificial intelligence on chest X-rays to triage COVID-19 suspects.

The diagnostic pathway for COVID-19

RT-PCR is the gold standard to confirm COVID-19. However, studies have shown that early stage of COVID-19 can be undetected by the lab test, where CT imaging is more likely to detect COVID-19 in early stages. CT imaging has shown to be a highly sensitive method to detect COVID-19.[1] It is a reliable, practical and rapid method to detect and assess COVID-19. X-ray, although not as sensitive as CT, is also used among patients presenting COVID-19 symptoms especially since it uses less radiation, and is often cheaper, quicker and easier to use than CT and more available in resource-constrained settings. Further benefits of X-ray are that they can be portable and thus used at the patient’s bedside. The power of radiology in this crisis is highlighted as such: a positive diagnosis from radiology is definitive, even when a lab test is negative.[2] Furthermore, radiology is an optimal method when it comes to assesing the progression of COVID-19 cases.

Click here for our FAQ about CAD4COVID

Why use artificial intelligence?

  • Reduce the workload of the health workforce
  • Enable quicker detection, therefore allowing for higher throughput
  • Enhance diagnostic infrastructure in resource constrained settings
  • Alleviate the burdens related to pathology tests.
  • Quantify disease progress and recovery

[1] Correlation of Chest CT and RT-PCR Testing in Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Case, Radiological Society of North America, February 26 2020; https://doi.org/10.1148/radiol.2020200642

[2] CT Imaging and Differential Diagnosis of COVID-19, Canadian Association of Radiologists Journal, March 4 2020; https://doi.org/10.1177/0846537120913033

Experts in screening across 40 countries

As companies that have built their foundation on improving diagnostics with innovative technology, we are committed to supporting the diagnosis of COVID-19 around the world. Thirona and Delft Imaging are active in 40 countries across the world. Delft Imaging focuses on developing countries and is stepping into the fight against COVID-19 to leverage its market access into Africa to ensure no community is left out.

We are proud to be collaborating on this initiative with our sister-company Thirona and our partners Bernhoven, Radboud University, HT Medica and Universitas Indonesia.

Our proven track record of artificial intelligence for image analysis

Our extensive history in tackling infectious diseases


The foundation for CAD4COVID is CAD4TB, which is the most extensively validated AI solution for tuberculosis detection.

Mozambique

Delft provided an EasyDR X-ray machine with our Computer Aided Detection for Tuberculosis software (CAD4TB). The X-ray screening on TB and silicosis, audio and other tests will be free of charge for all the migrating mine workers.

Swaziland

Early 2016, the National Tuberculosis Programme of Swaziland ordered a mobile OneStopTB clinic to screen around 100.000 inhabitants in Swaziland. They combined the EasyDR digital X-ray with the innovative CAD4TB software, which allowed for an instant triage of suspects. Besides this Delft delivered two EasyPortable X-rays to reach the remotest areas in the mountainous country.

Sierra Leone

In 2018, 12 digital X-ray systems were installed at the Connaught and at 10 district hospitals, through a tender by IDA Foundation that was Global Fund supported. These systems are entirely solar powered and include charging batteries that allow 4-6 hours of operation at night when grid power may be unavailable.