2023-06-22 12:00:00
A breast screening technology developed with the help of artificial intelligence (AI) can detect abnormalities that would have been missed with current screening methods, writes the University of Aberdeen in a press release.
The artificial intelligence detected abnormalities that would have been missed by current screening methods; The software recalled a third of the women who developed cancer between screenings;
The groundbreaking work by the University of Aberdeen, NHS Grampian and Kheiron Medical Technologies involved analyzing 220,000 mammograms from more than 55,000 people to determine how well an AI tool can detect breast cancer – from research to clinical application.
Kheiron Medical Technologies Ltd. The AI software developed called “Mia” was evaluated by a research team led by Professor Lesley Anderson, Chair of Health Data Science at the University of Aberdeen, as part of the Industrial Center for Artificial Intelligence Research in Digital Diagnostics (iCAIRD) program. dr Clarisse de Vries, a researcher in radiological imaging at the University of Aberdeen, led the data analysis.
Identification of overlooked cancers
The analysis found that Mia was successful in identifying potentially missed cancers, known as interval cancers, that are discovered between checkups. The team found that Mia would have suggested re-evaluating 34.1 percent of women who developed cancer between screenings. With current screening, these cancers go undetected until women develop symptoms.
dr De Vries explains: “Currently, two experts review each mammogram and decide whether the person should be invited for further examinations. If the two experts disagree, a third expert makes the final decision. Like a human expert, Mia can examine a screening mammogram and give an opinion on whether that person should be invited for further screening.
“We have shown that once artificial intelligence is tuned to the local environment, it can have tremendous benefits for clinicians and especially for people at risk of cancer.
improvement of health care
The consulting radiologist Dr. Gerald Lip was instrumental in bringing Mia into clinical practice: “When Mia was originally applied to the NHS Grampian data, it was too sensitive – it recommended recalling women for further investigation when that might not have been necessary . However, Mia’s performance improved significantly when it was adapted to local conditions and technology, allowing for the lowest possible number of women to be recalled while maintaining a high cancer detection rate.
“Until now, it has been unclear whether AI tools developed elsewhere can be used in different settings and screening centers. Now we know there are risks in simply taking an AI tool developed elsewhere and deploying it on-premises. You have to test the tool on the local data first to make sure it works as expected,” Lip said.
Professor Roger Staff, Head of Imaging Physics at NHS Grampian, added: “This is an important study that outlines the steps required to bring this technology to service. While the results suggest that the technology is not immediately operational, it does hold the potential for significant health and operational benefits for the service.”
#Groundbreaking #software #shines #breast #cancer #detection