“AI in diagnostics is the future. And I think our children will now look back on health care and think, “Oh my God, radiologists were just reading these images on their own?” » said Teri Thomas.
Thomas — CEO of Health Volparaa company that sells breast cancer screening software — made the comment during an interview this week at RSNA, the annual conference of the Radiological Society of North America. conference in Chicago.
She noted that Volpara’s belief that AI will shape the future of radiology played a major role in the company’s decision to sell in Lunit earlier this year. Lunit is a South Korean company specializing in AI tools for cancer diagnosis and therapy.
The deal allowed Volpara to share its in-depth knowledge of the U.S. healthcare system with Lunit, and helped Volpara build its AI expertise and capabilities, Thomas explained.
Working alongside Lunit leaders quickly deepened Thomas’ understanding of AI, she said. She highlighted a recent trip she took to Stockholm to visit St. Göran Hospitalwhich adopted Lunit’s AI solution for mammography this year.
“The standard for reading mammograms in Europe – and most other countries in the world outside the United States, for that matter – is that you have a radiologist who looks at the image and determines whether they think it is cancer or not, then they take a completely separate, unbiased look at it. Then they compare their results, and if they disagree, a third looks at them,” Thomas explained.
Given the current shortage of radiologists, there is a huge opportunity for AI to step into a process like this, she pointed out. And this is what is happening in Saint Göran.
“They have a radiologist, and then the RN is basically the second radiologist. They compare what the AI found with what the radiologist found, and if there is a disagreement, they bring in another radiologist,” she said.
At Saint Göran, the combination of one radiologist and AI outperforms two radiologists, Thomas said.
Radiologists train by looking at thousands of images, but not millions, she noted. She also pointed out that the way humans analyze images is “less systematic” than the way AI models have been trained.
“It’s like having a different angle. They call it a ‘second read,’ but it’s actually a second read that has been trained differently and may find different things,” Thomas explained.
The deal also helped Volpara integrate AI models into its software, she said.
The company is adding AI tools to help clinicians with various aspects of mammography, such as breast positioning, dosing and compression.
“Some people have learned (to squeeze) until (the patient) says, ‘Ouch, stop!’ » It’s horrible – there is such a thing as overcompression, and you actually don’t get as good a picture. There is also usually undercompression and you don’t get as good an image either. So, the application of AI can help determine what is the optimal compression, the best positioning, that the X-ray machine is appropriate and that the radiation dosage is correct,” Thomas remarked.
By adding these AI capabilities, Lunit and Volpara seek to make it easier and faster for clinicians to feel like they’ve gotten the most complete picture possible, she noted.
Photo: ipopba, Getty Images