Artificial intelligence to Screen for COVID-19 on CT- and X-ray images

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 leveraged our existing solutions and expertise on chest CT and chest X-ray and developed CAD4COVID: two artificial intelligence solutions – one for CT- and one for X-ray analysis. The two CAD4COVID solutions are intended to help triage COVID-19 suspects and inform on disease progression and recovery.

CAD4COVID-Xray and CAD4COVID-CT are built on the technical infrastructure of our existing CT- and X-ray solutions. LungQ is our existing Chest CT AI solution, which is FDA 510(k) cleared, CE 0344 marked, and TGA registered and processes data from over 350 hospitals on a daily basis. CAD4TB is our existing Chest X-ray AI solution; the software is CE 0344 marked and has been implemented in over 40 countries and screened more than 6 million people for TB.

As of June 10th 2020, both our CAD4COVID solutions are CE 0344 certified. We have already analyzed over 23,000 images (X-Ray and CT) from more than 210 hospitals and clinics in over 40 countries worldwide. The solutions will remain available free-of-charge in support of the COVID-19 crisis until at least June 2021.

CAD4COVID-CT

The goal of the CAD4COVID CT solution is to assess the suspicion of COVID-19 and to assess the severity of the infection based on the percent affected lung parenchyma. CAD4COVID-CT builds heavily on Thirona’s existing expertise in chest CT analysis using our product LungQ, which allowed us to move quickly and gather both knowledge and data through our network.

CAD4COVID CT-provides a segmentation of the pulmonary lobes and detects all COVID-19 related abnormalities on the CT scan. Using the detected abnormalities a scoring system is automatically filled in:

  • An overall severity score indicating the severity of the infection (0-5 points per lobe, maximum score 25 overall)
  • The severity score per lobe (0-5) indicating the severity of the infection in each lobe separately
  • The percent affected for each lobe

We also provide the percent emphysema present in each lobe. Emphysema is a common co-morbidity and a risk factor for severe illness from COVID-19.

Our CAD4COVID CT solution has been developed in collaboration with our partners at RadboudUMC, Fraunhofer MEVIS and HT Medica. The first version of CAD4COVID-CT was launched in the week of April 20 for investigational use. Next to offering CAD4COVID-CT through our own webportal, CAD4COVID is available through a collaboration with Smart Reporting, integrating it with their structured reporting capabilities.

An example of a report is shown below.

CAD4COVID-XRay

Together with Delft Imaging, we developed CAD4COVID-XRay: an artificial intelligence software that triages COVID-19 suspects on chest X-ray images. CAD4COVID-XRay has been developed with the intention to support triaging in resource-constrained settings and high-prevalence areas. It became 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.

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. The performance of CAD4COVID in detection of COVID-19 on chest X-ray images is comparable with that of human readers, as shown in an evaluation study published in Radiology.

Why implement Artificial Intelligence?

The reasons to use Artificial Intelligence are the following:

  • 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

How can you access CAD4COVID-CT

To receive access to CAD4COVID-CT on the CAD4COVID Cloud, please fill in the form below . By using CAD4COVID-CT, you confirm you have read and accept the Terms & Conditions that apply to CAD4COVID-CT, Thirona and our Privacy Policy.

Contact form

Contact Us
reCAPTCHA

How can you access CAD4COVID-XRay

CAD4COVID-XRay can be accessed by filling out the form at the bottom of the following 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.