EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Deep learning based automated left atrial segmentation and flow quantification of real time phase contrast MRI in patients with atrial fibrillation

Justin Baraboo, Amanda DiCarlo, Haben Berhane, Daming Shen, Rod Passman, Daniel C Lee, Patrick M McCarthy, Rishi Arora, Dan Kim, Michael Markl

The International Journal of Cardiovascular Imaging · 2025

DOI: 10.1007/s10554-025-03407-9 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift The International Journal of Cardiovascular Imaging, 2025. Verfasst von Justin Baraboo und 9 weiteren Autor:innen. Beteiligte Einrichtung: Northwestern Biomedical Engineering, Chicago, Illinois, USA. Justin.Baraboo@northwestern.edu. Hauptthemen laut MEDLINE: Atrial Fibrillation, Deep Learning, Heart Atria, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, National Institute of Biomedical Imaging And Bioengineering of the National Institutes of Health, NIA NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real time 2D phase contrast (RTPC) MRI is useful for flow quantification in atrial fibrillation (AF) patients, but data analysis requires time-consuming anatomical contouring for many cardiac time frames. Our goal was to develop a convolutional neural network (CNN) for fully automated left atrial (LA) flow quantification. Forty-four AF patients underwent cardiac MRI including LA RTPC, collecting a median of 358 timeframes per scan. 15,307 semi-manual derived RTPC LA contours comprised ground truth for CNN training, validation, and testing. CNN vs. human performance was assessed using Dice scores (DSC), Hausdorff distance (HD), and flow measures (stasis, velocities, flow). LA contour DSC across all patients were similar to human inter-observer DSC (0.90 vs. 0.93) and a median 4.6 mm [3.5–5.9 mm] HD. There was no impact of heart rate variability on contouring quality (low vs. high variability DSC: 0.92 ± 0.05 vs. 0.91 ± 0.03, p = 0.95). CNN based LA flow quantification showed good to excellent agreement with semi-manual analysis ( r > 0.90) and small bias in Bland-Altman analysis for mean velocity (-0.10 cm/s), stasis (1%), and net flow (-2.4 ml/s). This study demonstrated the feasibility of CNN based LA flow analysis with good agreements in LA contours and flow measures and resilience to heartbeat variability in AF.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Atrial FibrillationDeep LearningHeart AtriaImage Interpretation, Computer-AssistedAtrial Function, LeftMagnetic Resonance ImagingMagnetic Resonance Imaging, CineHumansPredictive Value of TestsMaleFemaleAgedReproducibility of ResultsMiddle AgedAutomationBlood Flow VelocityTime FactorsObserver VariationHeart Rate

Stichwörter der Autor:innen

Atrial fibrillationCardiac magnetic resonance imagingDeep learningImage processingReal time phase contrast

Autor:innen und Institutionen

  • Northwestern Biomedical Engineering, Chicago, Illinois, USA. Justin.Baraboo@northwestern.edu.
  • Northwestern Radiology, Chicago, Illinois, USA. Justin.Baraboo@northwestern.edu.
  • , 737 N. Michigan Avenue Suite 1600, Chicago, Illinois, 312694776, USA. Justin.Baraboo@northwestern.edu.
  • Northwestern Radiology, Chicago, Illinois, USA.
  • Northwestern Biomedical Engineering, Chicago, Illinois, USA.
  • Northwestern Medicine, Cardiology, Chicago, Illinois, USA.

Förderung

  • NHLBI NIH HHS
  • National Institute of Biomedical Imaging And Bioengineering of the National Institutes of Health
  • NIA NIH HHS
  • National Institute On Aging

Zitieren

APA

Baraboo, J., DiCarlo, A., Berhane, H., Shen, D., Passman, R., Lee, D. C., McCarthy, P. M., Arora, R., Kim, D., & Markl, M. (2025). Deep learning based automated left atrial segmentation and flow quantification of real time phase contrast MRI in patients with atrial fibrillation. The International Journal of Cardiovascular Imaging. https://doi.org/10.1007/s10554-025-03407-9

Vancouver

Baraboo J, DiCarlo A, Berhane H, Shen D, Passman R, Lee DC, et al. Deep learning based automated left atrial segmentation and flow quantification of real time phase contrast MRI in patients with atrial fibrillation. The International Journal of Cardiovascular Imaging. 2025. doi:10.1007/s10554-025-03407-9

BibTeX
@article{Baraboo2025,
  author = {Baraboo, Justin and DiCarlo, Amanda and Berhane, Haben and Shen, Daming and Passman, Rod and Lee, Daniel C and McCarthy, Patrick M and Arora, Rishi and Kim, Dan and Markl, Michael},
  title = {Deep learning based automated left atrial segmentation and flow quantification of real time phase contrast MRI in patients with atrial fibrillation},
  journal = {The International Journal of Cardiovascular Imaging},
  year = {2025},
  doi = {10.1007/s10554-025-03407-9}
}
Kostenlos starten →