ScreenPoint Medical has demonstrated the value of its AI-powered Transpara: Breast AI screening tool in a new study.
The Netherlands-based company’s Mammography Screening with Artificial Intelligence (MASAI) study of 105,000 women found that Transpara increased cancer detection by 29% and reduced screen-reading workload for radiologists by 44%.
Related: Newronika wins FDA IDE clearance for Adaptive DBS System clinical trial
ScreenPoint’s data highlights that Transpara detected 338 cancers among 53,043 participants which indicates a 29% detection increase, without increasing false positives, and a detection rate of 6.4 per 1,000 participants versus five per 1,000 in the control group.
According to the study’s researchers, the MASAI screen-reading procedure emphasised the importance of radiologists having access to breast AI lesion detection and risk information at screen reading to introduce a beneficial bias.
They stated that making radiologists aware of the cancer prevalence when reading low-risk and high-risk exams may influence them to reduce false positives in low cancer prevalence readings and reduce false negatives in high cancer prevalence readings by giving access to regional marks that highlight suspicious findings to lower the risk of overlooking potential findings.
Results from the study of Transpara, the latest version of which gained clearance from the US Food and Drug Administration (FDA) in December 2024, were published in The Lancet Digital Health.
