Study: AI set to improve breast cancer screenings with 'risk score'

London (dpa) – University of Cambridge researchers believe they have shown how artificial intelligence (AI) can narrow down who is most at risk of developing breast cancer between two scheduled mammograms. Published by the Radiological Society of North America (RSNA), the team used an AI bot called Mirai to assess around 134,000 mammograms to find cases where supplemental imaging might be needed after a regular screening ended with a negative or no-cancer result. The device generated what the team described as a "generalized risk score" for developing a so-called interval breast cancer – when the disease develops between mammograms – after checking information gleaned from a mammogram, such as tumour features and breast density. "We can use supplemental imaging and adjust screening frequency based on a woman’s breast density and likelihood of developing breast cancer within a short timeframe," said Fiona Gilbert, professor of radiology at the University of Cambridge, explaining where and when the AI tool could be used. The mammograms assessed were from British women aged between 50 and 70, screened between 2014 and 2016. "Interval cancers generally have a worse prognosis compared with screen-detected cancers, because they tend to be either larger or more aggressive," said Gilbert, also an honorary consultant radiologist at Cambridge's Addenbrooke's Hospital. "Identifying women at an increased risk of developing breast cancer is a complex, multifactorial problem," Gilbert said. The researchers said their goal was to more accurately identify the women "most likely to have an interval cancer" while simultaneously reducing the workload around taking supplemental images. The following information is not intended for publication dpa spr coh

(The article has been published through a syndicated feed. Except for the headline, the content has been published verbatim. Liability lies with original publisher.)