Brief Description

Medical imaging techniques, such as CT, MRI, and X-ray scans, have become an integral part of patient diagnosis and treatment around the globe. Although imaging technology has advanced significantly over the years, the human interpretation errors remain the same. Studies on average report a 3 – 5 % error rate in daily practice. However, when evaluating abnormal scans, there is an approximately one in three chance the medical problem is misdiagnosed even by an experienced radiologist.

Problem Statement

Computer-aided detection and diagnosis methods are being introduced into medical practice by acting as a prospective peer review tool for radiologists. However, there is an upper limit to how large and complex the AI models can become. Reaching satisfactory accuracy and reliability consumes a lot of computational power and can take weeks to train. To deal with growing machine learning model complexity, future machine learning models will require computational power of a quantum computer to deliver results in real-time.

Solution

We investigated quantum machine learning capabilities in medical image analysis and as a result built a prototype application QuRay that uses quantum machine learning algorithms to detect 8 the most common radiographic findings in the chest X-rays. Explore the demo application to see how the solution works and how it can be integrated in the radiologist and practitioner workflow.

Disclaimer

This Demo is for demonstration purposes only and not for any other intent. Accenture owns all rights, titles, and interests in this Demo. Accenture makes no representations or warranties regarding this Demo. To the extent permitted by law, Accenture disclaims all liability, including direct and indirect, incidental or consequential damages, including loss of profits, arising out of or relating to the use of this Demo. The laws designated by the Accenture entity providing this Demo will govern without referencing conflicts of law principles.