TY - GEN
T1 - Implicit neural representations for registration of left ventricle myocardium during a cardiac cycle
AU - Lowes, Mathias Micheelsen
AU - Pedersen, Jonas Jalili
AU - Hansen, Bjørn S.
AU - Kofoed, Klaus Fuglsang
AU - Sermesant, Maxime
AU - Paulsen, Rasmus R.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - Understanding the movement of the left ventricle myocardium (LVmyo) during the cardiac cycle is essential for assessing cardiac function. One way to model this movement is through a series of deformable image registrations (DIRs) of the LVmyo. Traditional deep learning methods for DIRs, such as those based on convolutional neural networks, often require substantial memory and computational resources. In contrast, implicit neural representations (INRs) offer an efficient approach by operating on any number of continuous points. This study extends the use of INRs for DIR to cardiac computed tomography (CT), focusing on LVmyo registration. To enhance the precision of the registration around the LVmyo, we incorporate the signed distance field of the LVmyo with the Hounsfield Unit values from the CT frames. This guides the registration of the LVmyo, while keeping the tissue information from the CT frames. Our framework demonstrates high registration accuracy and provides a robust method for temporal registration that facilitates further analysis of LVmyo motion.
AB - Understanding the movement of the left ventricle myocardium (LVmyo) during the cardiac cycle is essential for assessing cardiac function. One way to model this movement is through a series of deformable image registrations (DIRs) of the LVmyo. Traditional deep learning methods for DIRs, such as those based on convolutional neural networks, often require substantial memory and computational resources. In contrast, implicit neural representations (INRs) offer an efficient approach by operating on any number of continuous points. This study extends the use of INRs for DIR to cardiac computed tomography (CT), focusing on LVmyo registration. To enhance the precision of the registration around the LVmyo, we incorporate the signed distance field of the LVmyo with the Hounsfield Unit values from the CT frames. This guides the registration of the LVmyo, while keeping the tissue information from the CT frames. Our framework demonstrates high registration accuracy and provides a robust method for temporal registration that facilitates further analysis of LVmyo motion.
KW - Cardiac CT
KW - Deep Learning
KW - Deformable Image Registration
KW - Implicit Neural Representations
KW - Left Ventricle Myocardium
KW - Signed Distance Fields
UR - http://www.scopus.com/inward/record.url?scp=105004254498&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-87756-8_17
DO - 10.1007/978-3-031-87756-8_17
M3 - Article in proceedings
AN - SCOPUS:105004254498
SN - 978-3-031-87755-1
T3 - Lecture Notes in Computer Science
SP - 172
EP - 182
BT - Statistical Atlases and Computational Models of the Heart. Workshop, CMRxRecon and MBAS Challenge Papers
A2 - Camara, Oscar
A2 - Puyol-Antón, Esther
A2 - Sermesant, Maxime
A2 - Suinesiaputra, Avan
A2 - Zhao, Jichao
A2 - Wang, Chengyan
A2 - Tao, Qian
A2 - Young, Alistair
PB - Springer Science and Business Media Deutschland GmbH
T2 - 15th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2024, Held in Conjunction with MICCAI 2024
Y2 - 10 October 2024 through 10 October 2024
ER -