How is AI redefining radiology?

Artificial Intelligence (AI) technology is making a promising dent in the radiology field when it comes to early cancer detection. 

The new tool, Sybil, pinpoints where lung cancer is most likely to appear so the patient can start treatment as soon as possible. 

Developed by scientists at the Mass General Cancer Center and the Massachusetts Institute of Technology in Cambridge, the AI can detect lung cancer before doctors would be able to pick up on it in a CT scan. 

During the test period, the technology showed an 86% to 94% accuracy rate in predicting whether or not the subject would develop lung cancer in the next one to six years. 

Dr Lecia Sequist, oncologist and program director of the Cancer Early Detection and Diagnostics Clinic at Massachusetts General Hospital, says: “The naked eye cannot see everything. The AI that we developed is looking at the scan in a completely different way than a human radiologist looks at it.”

With lung cancer being the third most common cancer in the United States, it is hoped that Sybil will help prevent unnecessary deaths by spotting lung cancer in the early stages (during which time it is more treatable). 

Sadly, after patients present with symptoms such as persistent coughing and difficulty breathing, the cancer is much more challenging to cure. 

“This is great for radiologists, but more importantly, it’s really great for our patients to be able to give them that tool to tell them whether or not we think something is lung cancer,” added Dr Kim Sandler, an associate professor of radiology at Vanderbilt University Medical Center in Nashville, Tennesse. 

Whilst this new technology has spectacular potential, the risk of ‘overdiagnosis’ has been flagged by experts. This would mean a patient going through treatment only for doctors to eventually discover the nodule identified by the AI was benign. 

Sybil is yet to be approved by the Food and Drug Administration for use outside clinical trials in the United States. 

Here in the UK, AstraZeneca is working on developing a similar tool to help doctors diagnose lung cancer early on. 

The software, qXR, uses deep-learning algorithms to scan X-ray images for abnormalities. 

Amaré Health is excited to see the full potential of these AI tools unfold and we hope this technology will help make a difference in improving lung cancer survival rates through early detection. 

If you’re interested in working in radiology, give our team a call on 0203 929 4017 and we’ll take you through our current vacancies.