What are the Hurdles to Integrating AI Into Reading Workflow Today?

What is the AI Conversation Series?

Welcome to our AI conversation video series, where we answer nine of the most frequently asked and debated questions regarding artificial intelligence. These are the questions that you keep hearing at conferences, during webinars, and on social media. Each video reveals our answer to a challenging AI question in a quick and to-the-point manner. In our second video in the series, TeraRecon President and CEO, Jeff Sorenson breaks down the most common hurdles to AI integration into the radiology today and how we have overcome those hurdles.

If you missed the first video in our series, click here to watch it now!

AI Integration Hurdles

Essentially the challenge that physicians are having, in terms of their workflow today, is that there is no way to put AI in the workflow today. If you were to poll a room of 300 physicians, zero would have access to these tools in their routine clinical practice.

Now, there are a number of reasons for that in terms of the PACS systems being unable to actually ingest the kind of findings that AI makes, and also in terms of the ability to store it, to recall it, to create an interactive experience where the physician knows what the AI is doing. Right now, we are in a situation where there is a black box that no one understands and there is a system that they use every day that can’t actually work with that kind of data.

So what we’ve done is create a system that will rationalize the inputs and outputs of many different kind of AI so that they can be used in a standard way, and we even created the tools that can be embed into their PACs to will allow them to experience and experiment with this AI and embed it into their workflow without any type of special update to their PACS systems.