Multimodal Learning To Improve Cardiac Late Mechanical Activation Detection From Cine MR Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xing, Jiarui, Wu, Nian, Bilchick, Kenneth, Epstein, Frederick, Zhang, Miaomiao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916141702578176
author Xing, Jiarui
Wu, Nian
Bilchick, Kenneth
Epstein, Frederick
Zhang, Miaomiao
author_facet Xing, Jiarui
Wu, Nian
Bilchick, Kenneth
Epstein, Frederick
Zhang, Miaomiao
contents This paper presents a multimodal deep learning framework that utilizes advanced image techniques to improve the performance of clinical analysis heavily dependent on routinely acquired standard images. More specifically, we develop a joint learning network that for the first time leverages the accuracy and reproducibility of myocardial strains obtained from Displacement Encoding with Stimulated Echo (DENSE) to guide the analysis of cine cardiac magnetic resonance (CMR) imaging in late mechanical activation (LMA) detection. An image registration network is utilized to acquire the knowledge of cardiac motions, an important feature estimator of strain values, from standard cine CMRs. Our framework consists of two major components: (i) a DENSE-supervised strain network leveraging latent motion features learned from a registration network to predict myocardial strains; and (ii) a LMA network taking advantage of the predicted strain for effective LMA detection. Experimental results show that our proposed work substantially improves the performance of strain analysis and LMA detection from cine CMR images, aligning more closely with the achievements of DENSE.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18507
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multimodal Learning To Improve Cardiac Late Mechanical Activation Detection From Cine MR Images
Xing, Jiarui
Wu, Nian
Bilchick, Kenneth
Epstein, Frederick
Zhang, Miaomiao
Computer Vision and Pattern Recognition
This paper presents a multimodal deep learning framework that utilizes advanced image techniques to improve the performance of clinical analysis heavily dependent on routinely acquired standard images. More specifically, we develop a joint learning network that for the first time leverages the accuracy and reproducibility of myocardial strains obtained from Displacement Encoding with Stimulated Echo (DENSE) to guide the analysis of cine cardiac magnetic resonance (CMR) imaging in late mechanical activation (LMA) detection. An image registration network is utilized to acquire the knowledge of cardiac motions, an important feature estimator of strain values, from standard cine CMRs. Our framework consists of two major components: (i) a DENSE-supervised strain network leveraging latent motion features learned from a registration network to predict myocardial strains; and (ii) a LMA network taking advantage of the predicted strain for effective LMA detection. Experimental results show that our proposed work substantially improves the performance of strain analysis and LMA detection from cine CMR images, aligning more closely with the achievements of DENSE.
title Multimodal Learning To Improve Cardiac Late Mechanical Activation Detection From Cine MR Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.18507