AI Program Could Aid Decision-Making in Medical Imaging

Raytheon BBN Technologies (Cambridge, MA, USA) is developing the neural network under the Defense Research Project Agency's (DARPA) Explainable Artificial Intelligence program (XAI). The aim of the XAI program is to create a suite of machine learning techniques, which produce more explainable models while maintaining a high level of performance. It also aims to help human users understand, appropriately trust and effectively manage the emerging generation of artificially intelligent partners.

The Explainable Question Answering System (EQUAS) by Raytheon BBN will allow Artificial Intelligence (AI) programs to 'show their work,' increasing the human user's confidence in the machine's suggestions. EQUAS will show users which data mattered most in the AI decision-making process. Using a graphical interface, users can explore the system's recommendations and see why it chose one answer over another. Although the technology is still in its early phases of development, it has the potential to be used for a wide-range of applications. As the system is enhanced, EQUAS will be able to monitor itself and share factors that limit its ability to make reliable recommendations. This self-monitoring capability will help developers refine AI systems, allowing them to inject additional data or change how data is processed.

"A fully developed system like EQUAS could help with decision-making not only in DoD operations, but in a range of other applications like campus security, industrial operations and the medical field," said Bill Ferguson, lead scientist and EQUAS principal investigator at Raytheon BBN. "Say a doctor has an x-ray image of a lung and her AI system says that its cancer. She asks why and the system highlights what it thinks are suspicious shadows, which she had previously disregarded as artifacts of the X-ray process. Now the doctor can make the call – to diagnose, investigate further, or, if she still thinks the system is in error, to let it go."

Related Links:
Raytheon BBN Technologies