How is AI Impacting Medical X-ray Imaging?

We hear a lot of buzz regarding how artificial intelligence (AI) will affect our future, but we don’t hear much in everyday conversation on how they will impact the X-ray space. AI technology is currently being used heavily in radiology to improve diagnosis.

​Qure.ai, an Indian health-tech startup based in Mumbai has created a technology powered by AI that examines X-rays, MRI’s and CT scans. It also helps identify patients diagnosed with diseases such as TB or a stroke and develop reliable reports quickly.

As stated in this article “…AI technology involves the application of deep learning algorithms to detect and highlight abnormalities in medical imaging like chest X-rays, MRIs and CT scans. It aims to significantly scale and improve the diagnosis of diseases, especially TB, in the country.”

Prashant Warier, Qure.ai’s co-founder said that he based his technology on artificial neural networks trained by presenting an algorithm with an extensive collection of cases. Radiologist train in virtually the same way.

“We have shown the algorithm 1.5 million X-rays, some normal and others abnormal. And trained them to understand what an abnormality would look like. Techniques like deep learning have made it possible to automatically identify multiple disease states from a medical image,” he said. As of today, Qure.ai’s technology is undergoing evaluation for use at public health centers in Maharashtra.

Several researchers and companies are also looking to make an impact in radiology via AI.  A group at Stanford Department of Computer Science and Stanford Medical School created an AI radiology system to more accurately diagnose pneumonia on chest radiographs.

Pneumonia is the 6th leading cause of death in the United States. If diagnosed and treated within 4 hours, the survival rates of those affected will increase dramatically. The team at Stanford trained the AI system, CheXNet, using over 100,000 X-ray images from the National Institutes of Health. With just over one month of practice, the AI was able to diagnose pneumonia better than the four radiologists with whom it was competing.

Interested in learning more about how AI will impact the field of radiology? Check back next week to find out more.