Peer-Reviewed Publication
Eur J Radiol2025;192112356.November 1, 2025Journal Article
Dynamic AI-assisted ipsilateral tissue matching for digital breast tomosynthesis.
Stephen Morrell1, Michael Hutel2, Oeslle Lucena3, Cristina Alfaro V4, Georgiana Zamfir5, Charlottefreya Longman5, Rumana Rahim5, Sophia O'Brien6, Elizabeth S McDonald6, Samantha P Zuckerman6, John R Scheel7, Anna Metafa8, Nisha Sharma9, Sebastien Ourselin2, Jorge Cardoso2, Juliet Morel5, Keshthra Satchithananda5, Emily F Conant6
1King's College London, London, UK; Elaitra Ltd., London, UK. Electronic address: stephen.morrell@kcl.ac.uk.
2King's College London, London, UK; Elaitra Ltd., London, UK.
3King's College London, London, UK.
4Department of Medical Technology, Universidad de Tarapacá, Arica, Chile.
5King's College Hospital NHS Foundation Trust, London, UK.
6Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, PA, USA.
7Department of Radiology, Vanderbilt University Medical Center, Nashville, TN, USA.
8Princess Royal University Hospital, Orpington, UK.
9Leeds Teaching Hospitals NHS Trust, Leeds, UK.
Abstract
PURPOSE: To evaluate whether AI-assisted ipsilateral tissue matching in digital breast tomosynthesis (DBT) reduces localization errors beyond typical tumor boundaries, particularly for non-expert radiologists. The technology category is deep learning.
MATERIALS AND METHODS: The study consisted of two parts. In Part 1, 14 radiologists subjectively evaluated the AI tool's impact on confidence and p…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans