EUVIMEDEUVIMED entdecken
Open Access

Deep Learning–based Aligned Strain from Cine Cardiac MRI for Detection of Fibrotic Myocardial Tissue in Patients with Duchenne Muscular Dystrophy

Sven Koehler iD, Julian Kuhm iD, Tyler Huffaker, Daniel Young, Animesh Tandon, Florian André iD, Norbert Frey, Gerald Greil iD, Tarique Hussain, Sandy Engelhardt iD

Radiology: Artificial Intelligence · 2025

DOI: 10.1148/ryai.240303 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology: Artificial Intelligence, 2025. Verfasst von Sven Koehler und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Internal Medicine III, Heidelberg University Hospital, Im Neuenheimer Feld 410, 69120 Heidelberg, Germany. Hauptthemen laut MEDLINE: Muscular Dystrophy, Duchenne, Magnetic Resonance Imaging, Cine, Deep Learning, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, Klaus Tschira Foundation, Deutsches Zentrum für Herz-Kreislaufforschung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Phase-specific strain derived from cine cardiac MRI, temporally aligned between patients, identified five times more differences between fibrotic and nonfibrotic segments compared with traditional strain measurements in patients with Duchenne muscular dystrophy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Muscular Dystrophy, DuchenneMagnetic Resonance Imaging, CineDeep LearningImage Interpretation, Computer-AssistedCardiomyopathiesHumansMaleRetrospective StudiesAdolescentFibrosisChildReproducibility of ResultsMyocardiumHeart

Stichwörter der Autor:innen

CardiacConvolutional Neural Network (CNN) Duchenne Muscular DystrophyHeartImage PostprocessingPediatrics

Autor:innen und Institutionen

  • Department of Internal Medicine III, Heidelberg University Hospital, Im Neuenheimer Feld 410, 69120 Heidelberg, Germany.
  • German Centre for Cardiovascular Research (DZHK), Partner Sites Heidelberg and Mannheim, Germany.
  • Medical Faculty of University Heidelberg, Heidelberg University, Heidelberg, Germany.
  • Division of Pediatric Cardiology, Department of Pediatrics, UT Southwestern/Children's Health, Dallas, Tex.
  • Department of Heart, Vascular, and Thoracic, Children's Institute; Cleveland Clinic Children's Centre for Artificial Intelligence (C4AI); and Cardiovascular Innovation Research Centre, Cleveland Children's Clinic, Cleve…
  • Department of Biomedical Engineering, Case School of Engineering, Case Western Reserve University, Cleveland, Ohio.

ORCID-Profile: Sven Koehler, Julian Kuhm, Florian André, Gerald Greil, Sandy Engelhardt

Förderung

  • NHLBI NIH HHS
  • Klaus Tschira Foundation
  • Deutsches Zentrum für Herz-Kreislaufforschung
  • Deutsche Forschungsgemeinschaft
  • Carl-Zeiss-Stiftung
  • National Institutes of Health

Zitieren

APA

Koehler, S., Kuhm, J., Huffaker, T., Young, D., Tandon, A., André, F., Frey, N., Greil, G., Hussain, T., & Engelhardt, S. (2025). Deep Learning–based Aligned Strain from Cine Cardiac MRI for Detection of Fibrotic Myocardial Tissue in Patients with Duchenne Muscular Dystrophy. Radiology: Artificial Intelligence. https://doi.org/10.1148/ryai.240303

Vancouver

Koehler S, Kuhm J, Huffaker T, Young D, Tandon A, André F, et al. Deep Learning–based Aligned Strain from Cine Cardiac MRI for Detection of Fibrotic Myocardial Tissue in Patients with Duchenne Muscular Dystrophy. Radiology: Artificial Intelligence. 2025. doi:10.1148/ryai.240303

BibTeX
@article{Koehler2025,
  author = {Koehler, Sven and Kuhm, Julian and Huffaker, Tyler and Young, Daniel and Tandon, Animesh and André, Florian and Frey, Norbert and Greil, Gerald and Hussain, Tarique and Engelhardt, Sandy},
  title = {Deep Learning–based Aligned Strain from Cine Cardiac MRI for Detection of Fibrotic Myocardial Tissue in Patients with Duchenne Muscular Dystrophy},
  journal = {Radiology: Artificial Intelligence},
  year = {2025},
  doi = {10.1148/ryai.240303}
}
Kostenlos starten →