Generalizable attention U-Net for segmentation of fibroglandular tissue and background parenchymal enhancement in breast DCE-MRI.

Sylwia NowakowskaKarol BorkowskiCarlotta M RuppertAnna LandsmannMagda MarconNicole BergerAndreas BossAlexander CiritsisCristina Rossi

Published in: Insights into imaging (2023)

• Our work contributes to the standardization of FGT and BPE assessment. • Attention U-Net can reliably segment intricately shaped FGT and BPE structures. • The developed models were robust to domain shift.

Keyphrases

working memory
contrast enhanced
magnetic resonance imaging
deep learning
convolutional neural network
high resolution
diffusion weighted imaging
computed tomography
magnetic resonance