AI-assisted cancer screening could cut the radiologist’s workload in half

A recently published study in the have found that the use of AI in mammography cancer screening can safely cut the radiologist’s workload in half without the risk of increasing false-positive results. In fact, the study found that AI’s recommendations were .

“AI-assisted mammography screening resulted in a similar cancer detection rate compared to standard double-reading, with a significantly lower screen-reading workload, indicating that the use of AI in mammography screening is safe,” the study found.

The study was carried out by a research team from Lund University in Sweden and consequently followed 80,033 Swedish women (average age 54) for just over a year in 2021-2022. Of the 39,996 patients randomly assigned to AI-enabled breast cancer screenings, 28 percent, or 244 tests, returned screen-detected cancers. Of the other 40,024 patients who received conventional cancer screenings, only 25 percent, or 203 tests, returned screen-detected cancers.

Of the additional 41 cancers detected by the AI ​​site, 19 were found to be invasive. Both the AI-enabled and conventional screenings had a false positive rate of 1.5 percent. Most impressively, radiologists on the AI ​​side had to look at 36,886 fewer screen readings than their counterparts, a 44 percent reduction in their workload.

“These promising preliminary safety results should be used to inform new trials and program-based evaluations to address the pronounced shortage of radiologists in many countries, but they are not enough alone to confirm that AI is ready to be implemented in mammography screening.” lead author, Dr. Kristina Lång, warned in a message. “We still need to understand the implications for patient outcomes, particularly whether the combination of radiologists’ expertise with AI can help detect interval cancers that are often missed by traditional screening, as well as the cost-effectiveness of the technology.”

Cancer detection has been an aspirational goal for computer vision researchers and AI companies for years now. I mean, who wouldn’t want to be the company to build the tricorder that unfailingly detects cancer growths in their earliest stages? Machine vision systems designed for these screenings have and have in specific cases been shown to be , with the likes of , , and investing in similar cancer screening research in recent years.