Automatic segmentation of multiple cardiovascular structures from cardiac computed tomography angiography images using deep learning.

Lohendran BaskaranSubhi J Al'ArefGabriel MaliakalBenjamin C LeeZhuoran XuJeong W ChoiSang-Eun LeeJi Min SungFay Y LinSimon DunhamBobak MosadeghYong-Jin KimIlan GottliebByoung Kwon LeeEun Ju ChunFilippo CademartiriErica MaffeiHugo MarquesSanghoon ShinJung Hyun ChoiKavitha ChinnaiyanMartin HadamitzkyEdoardo ConteDaniele AndreiniGianluca PontoneMatthew J BudoffJonathon A LeipsicGilbert L RaffRenu VirmaniHabib SamadyPeter H StoneDaniel S BermanJagat NarulaJeroen J BaxHyuk-Jae ChangJames K MinLeslee J Shaw

Published in: PloS one (2020)

An automated deep learning model demonstrated segmentation of multiple cardiovascular structures from CCTA images with reasonable overall accuracy when evaluated on a pixel level.

Keyphrases

deep learning
convolutional neural network
artificial intelligence
high resolution
machine learning
left ventricular
computed tomography
mass spectrometry