Smart Technology for Diagnosing
Artificial intelligence and computer aided diagnosis (CAD) technologies are on the cutting edge of medical imaging, detection, and diagnosis. Smart technology is becoming increasingly popular as it can help to reduce false positives as a consequence of fatigue and bias from radiologists. The NIH Clinical Center has developed a CAD and eye-tracking system for radiology reading.
This CAD technology has been developed in order to reduce diagnostic errors. Currently, there is a certain percentage of potentially cancerous image features that are overlooked by radiologists as a result of human error, fatigue, and the complexity of performing a visual search. This system helps to improve radiologist’s diagnostic decisions during screening and diagnosis by monitoring where they have looked and tracking where they have a history of under-looking.
This new technology works by using an eye-tracking interface and utilizing novel algorithms to unify eye-tracking data and a CAD system. The system works by coordinating the eye-tracking data and processing gaze patterns simultaneously with a deep learning algorithm in a multi-task learning platform to segment and assist the diagnosis of suspicious image features. Testing of the system in a lung cancer screening experiment with multiple radiologists has shown improved accuracy in reducing false positives.
This exciting technology is available for licensing and research collaboration from the NIH Clinical Center. More information can be found here.