EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MyoNet: Deep Learning-Based Myocardial Strain Quantification from Cine Cardiac MRI

Dayeong An iD, Andrew Nencka iD, Patrick Clarysse iD, Pierre Croisille, Carmen Bergom iD, El-Sayed Ibrahim iD

Bioengineering · 07.03.2026 · 13 (3) · 310

DOI: 10.3390/bioengineering13030310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 07.03.2026. Verfasst von Dayeong An und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Northwestern University, Chicago, IL 60611, USA. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To develop and assess MyoNet, a deep learning (DL)-based network for measuring myocardial regional function from cine cardiac magnetic resonance (CMR) images, and compare its efficacy with ResMyoNet as an efficient alternative to SinMod-derived reference. MyoNet was tested alongside ResMyoNet on datasets from Dahl salt-sensitive rat models undergoing radiation therapy (RT). Both networks were designed to extract displacement maps from cine images, were specifically optimized for detailed myocardial deformation, employed advanced convolution operations with alternating kernel sizes for spatial and temporal analysis, and robust loss functions. MyoNet demonstrated superior performance in myocardial strain measurement, achieving high consistency with the SinMod-derived reference strains. It outperformed ResMyoNet, achieving higher performance metrics, including SSIM of 0.961 and 0.960, ICC of 0.973 and 0.975, and Pearson CC of 0.973 and 0.953 for circumferential (Ecc) and radial (Err) strains, respectively. Its accuracy and efficiency in generating strain measurements were validated through comprehensive statistical analyses. MyoNet offers a significant advancement in myocardial strain analysis from cine CMR images, potentially revolutionizing cardiac imaging in pre-clinical studies. Its ability to provide detailed and reliable measurements positions it as a valuable tool for clinical applications, particularly in monitoring the cardiac health of cancer patients.

Schlagwörter

Stichwörter der Autor:innen

CMR taggingcardiac dysfunctioncardiac motion estimationcine cardiac MRIcircumferential straindeep learningmyocardial strainradial strainregional myocardial function

Autor:innen und Institutionen

  • Department of Radiology, Northwestern University, Chicago, IL 60611, USA.
  • Department of Radiology, Medical College of Wisconsin, Milwaukee, WI 53226, USA.
  • CREATIS, 69621 Lyon, France.
  • Department of Radiation Oncology, Washington University, St. Louis, MO 63110, USA.

ORCID-Profile: Dayeong An, Andrew Nencka, Patrick Clarysse, Carmen Bergom, El-Sayed Ibrahim

Zitieren

APA

An, D., Nencka, A., Clarysse, P., Croisille, P., Bergom, C., & Ibrahim, E. S. (2026). MyoNet: Deep Learning-Based Myocardial Strain Quantification from Cine Cardiac MRI. Bioengineering, 13(3), 310. https://doi.org/10.3390/bioengineering13030310

Vancouver

An D, Nencka A, Clarysse P, Croisille P, Bergom C, Ibrahim ES. MyoNet: Deep Learning-Based Myocardial Strain Quantification from Cine Cardiac MRI. Bioengineering. 2026;13(3):310. doi:10.3390/bioengineering13030310

BibTeX
@article{An2026,
  author = {An, Dayeong and Nencka, Andrew and Clarysse, Patrick and Croisille, Pierre and Bergom, Carmen and Ibrahim, El-Sayed},
  title = {MyoNet: Deep Learning-Based Myocardial Strain Quantification from Cine Cardiac MRI},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {3},
  pages = {310},
  doi = {10.3390/bioengineering13030310}
}
Kostenlos starten →