AI for medical imaging — now?

The ‘doctor’ will see you now…

Rupert Thomas
Towards Data Science

Interpreting medical imaging (x-rays, CT, MRI) scans is a highly-skilled, manual job requiring many years of training. Demand for imaging outstrips supply of qualified radiologists and this trend is likely to continue with an aging population and growing access to technological healthcare solutions in emerging markets. Is AI and computer vision ready to help?

For the first time, a computer can diagnose patients without a doctor’s interpretation.

AI and computer vision have long been envisaged as a root to faster, more accurate diagnoses. Stringent regulatory requirements for certification and validation of medical devices mean that it can be slow for new technologies to enter front-line clinical practice. Decision support tools based around deep learning are gaining acceptance, however, and several are already in use in clinics and hospitals. In this article we will examine six products that have already been approved for clinical use, looking at their route to market and any publicly available details of the underlying algorithms.

All medical software — including AI decision support tools — must be compliant with the relevant standards. Certification can be a costly exercise, requiring clinical trials to…

Create an account to read the full story.

The author made this story available to Medium members only.
If you’re new to Medium, create a new account to read this story on us.

Or, continue in mobile web

Already have an account? Sign in

No responses yet

What are your thoughts?