Cover Image

Artificial Intelligence to derive aligned strain in cine CMR to detect patients with myocardial fibrosis: an open and scrutinizable approach

Cine Cardiac Magnetic Resonance (CMR) is the gold standard for cardiac function evaluation, incorporating ejection fraction (EF) and strain as vital indicators of abnormal deformation. Rare pathologies like Duchenne muscular dystrophies (DMD) are monitored with repeated late gadolinium-enhanced (LGE...

Full description

Saved in:
Bibliographic Details
Main Authors: Köhler, Sven (Author) , Kuhm, Julian (Author) , Huffaker, Tyler (Author) , Young, Daniel (Author) , Tandon, Animesh (Author) , André, Florian (Author) , Frey, Norbert (Author) , Greil, Gerald (Author) , Hussain, Tarique (Author) , Engelhardt, Sandy (Author)
Format: Article (Journal) Chapter/Article
Language:English
Published: 04 Jan, 2024
In: Research Square
Year: 2024, Pages: 1-21
ISSN:2693-5015
DOI:10.21203/rs.3.rs-3785677/v1
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.21203/rs.3.rs-3785677/v1
Verlag, kostenfrei, Volltext: https://www.researchsquare.com/article/rs-3785677/v1
Get full text
Author Notes:Sven Koehler, Julian Kuhm, Tyler Huffaker, Daniel Young, Animesh Tandon, Florian Andre, Norbert Frey, Gerald Greil, Tarique Hussain, Sandy Engelhardt
Description
Summary:Cine Cardiac Magnetic Resonance (CMR) is the gold standard for cardiac function evaluation, incorporating ejection fraction (EF) and strain as vital indicators of abnormal deformation. Rare pathologies like Duchenne muscular dystrophies (DMD) are monitored with repeated late gadolinium-enhanced (LGE) CMR for identification of myocardial fibrosis. However, it is judicious to reduce repeated gadolinium exposure and rather employ strain analysis from cine CMR. This solution is limited so far since full strain curves are not comparable between individual cardiac cycles and current practice mainly neglects diastolic deformation patterns. Our novel Deep Learning-based approach derives strain values aligned by key frames throughout the cardiac cycle. In a reproducibility scenario (57+82 patients), our results reveal five times more significant differences (22 vs. 4) between patients with scar and without, enhancing scar detection by +30%, improving detection of patients with preserved EF by +61%, with an overall sensitivity/specificity of 82/81%.
Item Description:Gesehen am 01.04.2025
Physical Description:Online Resource
ISSN:2693-5015
DOI:10.21203/rs.3.rs-3785677/v1

Similar Items