Premium
Nonrigid active shape model–based registration framework for motion correction of cardiac T 1 mapping
Author(s) -
ElRewaidy Hossam,
Nezafat Maryam,
Jang Jihye,
Nakamori Shiro,
Fahmy Ahmed S.,
Nezafat Reza
Publication year - 2018
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.27068
Subject(s) - artificial intelligence , nuclear medicine , computer science , image registration , image quality , breathing , mathematics , computer vision , pattern recognition (psychology) , medicine , image (mathematics) , anatomy
Purpose Accurate reconstruction of myocardial T 1 maps from a series of T 1 ‐weighted images consists of cardiac motions induced from breathing and diaphragmatic drifts. We propose and evaluate a new framework based on active shape models to correct for motion in myocardial T 1 maps. Methods Multiple appearance models were built at different inversion time intervals to model the blood‐myocardium contrast and brightness changes during the longitudinal relaxation. Myocardial inner and outer borders were automatically segmented using the built models, and the extracted contours were used to register the T 1 ‐weighted images. Data acquired from 210 patients using a free‐breathing acquisition protocol were used to train and evaluate the proposed framework. Two independent readers evaluated the quality of the T 1 maps before and after correction using a four‐point score. The mean absolute distance and Dice index were used to validate the registration process. Results The testing data set from 180 patients at 5 short axial slices showed a significant decrease of mean absolute distance (from 3.3 ± 1.6 to 2.3 ± 0.8 mm, P < 0.001) and increase of Dice (from 0.89 ± 0.08 to 0.94 ± 0.4%, P < 0.001) before and after correction, respectively. The T 1 map quality improved in 70 ± 0.3% of the motion‐affected maps after correction. Motion‐corrupted segments of the myocardium reduced from 21.8 to 8.5% ( P < 0.001) after correction. Conclusion The proposed method for nonrigid registration of T 1 ‐weighted images allows T 1 measurements in more myocardial segments by reducing motion‐induced T 1 estimation errors in myocardial segments. Magn Reson Med 80:780–791, 2018. © 2018 International Society for Magnetic Resonance in Medicine.