Cardiovascular magnetic resonance images with susceptibility artifacts: artificial intelligence with spatial-attention for ventricular volumes and mass assessment.

Marco PensoMario BabbaroSara MocciaMarco GuglielmoMaria Ludovica CarerjCarlo Maria GiacariMattia ChiesaRiccardo MaragnaMark G RabbatAndrea BarisonNicola MartiniMauro PepiEnrico G CaianiGianluca Pontone

Published in: Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance (2022)

Experimental results show that the proposed method reached promising performance in cardiac segmentation from CMR images with susceptibility artifacts and alleviates time consuming expert physician contour segmentation.

Keyphrases

deep learning
artificial intelligence
convolutional neural network
magnetic resonance
big data
left ventricular
machine learning
image quality
heart failure
emergency department
primary care
working memory
clinical practice
mouse model
computed tomography
contrast enhanced