Improving Classification of Pneumonia in Chest X-ray (CXR) images

Publish date:

With the rise of COVID-19, medical facilities were operating beyond peak capacity. Capgemini has developed a Deep Learning based classification system that can distinguish between pneumonia and non-pneumonia cases as well as between viral (including COVID-19) and bacterial cases in seconds.

The aim of the project is to support the diagnosis of pneumonia and thus reduce the overall workload of medical staff. This MVP was presented on the AIforGood 2020 Summit organized by ITU.

The algorithm thus developed as part of our solution led to an improved classification of X-ray in the distinction between pneumonia and non-pneumonia cases, which in turn led to a reduction in the number of false negatives.

Although initially developed for accurately classifying pneumonia cases, this solution is also relevant for other fields of classification.

Download the story to know more or reach out to our experts to explore further possibilities.

POV - Improving Classification...

File size: 1.87 MB File type: PDF

Related Resources

Artificial Intelligence

Humanizing the AI experience for consumer goods and retail

Customers are looking for context-aware AI. How can companies deliver?

Artificial Intelligence

Envisioning Cardiac Electrophysiology with Artificial Intelligence

Cardiac arrhythmias are a major global healthcare problem and there is significant scope for...


By continuing to navigate on this website, you accept the use of cookies.

For more information and to change the setting of cookies on your computer, please read our Privacy Policy.


Close cookie information