Abstract
We examined the potential change in cancer detection when using an artificial intelligence (AI) cancer-detection software to triage certain screening examinations into a no radiologist work stream, and then after regular radiologist assessment of the remainder, triage certain screening examinations into an enhanced assessment work stream. The purpose of enhanced assessment was to simulate selection of women for more sensitive screening promoting early detection of cancers that would otherwise be diagnosed as interval cancers or as next-round screen-detected cancers. The aim of the study was to examine how AI could reduce radiologist workload and increase cancer detection. In this retrospective simulation study, all women diagnosed with breast cancer who attended two consecutive screening rounds were included. Healthy women were randomly sampled from the same cohort; their observations were given elevated weight to mimic a frequency of 0·7% incident cancer per screening interval. Based on the prediction score from a commercially available AI cancer detector, various cutoff points for the decision to channel women to the two new work streams were examined in terms of missed and additionally detected cancer. 7364 women were included in the study sample: 547 were diagnosed with breast cancer and 6817 were healthy controls. When including 60%, 70%, or 80% of women with the lowest AI scores in the no radiologist stream, the proportion of screen-detected cancers that would have been missed were 0, 0·3% (95% CI 0·0-4·3), or 2·6% (1·1-5·4), respectively. When including 1% or 5% of women with the highest AI scores in the enhanced assessment stream, the potential additional cancer detection was 24 (12%) or 53 (27%) of 200 subsequent interval cancers, respectively, and 48 (14%) or 121 (35%) of 347 next-round screen-detected cancers, respectively. Using a commercial AI cancer detector to triage mammograms into no radiologist assessment and enhanced assessment could potentially reduce radiologist workload by more than half, and pre-emptively detect a substantial proportion of cancers otherwise diagnosed later. Stockholm City Council.
Highlights
Population-wide breast cancer screening programmes have been successful in lowering breast cancer mortality and adherence to regular screening is high.[1,2] there are two issues that have not been fully addressed: the massive number of radiologist hours spent on assessing mainly healthy women and the relatively large proportion of women whose cancer is not detected during screening, despite regular screening participation
Added value of this study In this retrospective simulation study we show that a commercial artificial intelligence (AI) cancer-detector algorithm could be used in triaging mammograms to decrease radiologist time spent on clearly negative mammograms, and use these resources for women at risk of having a false-negative screening
Our research focuses on AI as an independent reader. In this retrospective simulation study, we examined triaging based on two complementary roles for a commercially available AI cancer detector: as the first and only reader to dismiss the majority of normal mammograms, and as the final reader after a negative examination to identify women at highest risk of undetected cancer
Summary
Population-wide breast cancer screening programmes have been successful in lowering breast cancer mortality and adherence to regular screening is high.[1,2] there are two issues that have not been fully addressed: the massive number of radiologist hours spent on assessing mainly healthy women and the relatively large proportion of women whose cancer is not detected during screening, despite regular screening participation. Among 1000 women who attend one screening exam ination in biennial screening programmes, approxi mately five women will have their cancer detected, and two women will have a normal screening assessment and be diagnosed clinically with breast cancer in the interval before the planned screening (interval cancer).[3] To further add to the improvement potential in early detection, around 20% of screen-detected cancers are large (>2 cm), making it probable that many of these cancers could have been detected on previous screening if MRI had been used.[4,5,6] MRI is costly, time consuming, and not realistic to use as a first-line screening modality for all women. There is a need for a triaging model to identify the mammograms for which radiologist assessment is unnecessary and to identify the women at highest risk of leaving screening facilities with undetected cancer
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
