EUVIMEDEUVIMED entdecken
Crossref

Deep Learning‐Based Analysis of Aortic Morphology From Three‐Dimensional MRI

Jia Guo iD, Kevin Bouaou, Sophia Houriez-Gombaud-Saintonge, Moussa Gueda, Umit Gencer, Vincent Nguyen, Etienne Charpentier, Gilles Soulat iD, Alban Redheuil, Elie Mousseaux iD, Nadjia Kachenoura, Thomas Dietenbeck iD

Journal of Magnetic Resonance Imaging · 2024

DOI: 10.1002/jmri.29236 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2024. Verfasst von Jia Guo und 11 weiteren Autor:innen. Beteiligte Einrichtung: Sorbonne Université, INSERM, CNRS, Laboratoire d'Imagerie Biomédicale (LIB), Paris, France. Hauptthemen laut MEDLINE: Deep Learning, Imaging, Three-Dimensional, Aorta, Magnetic Resonance Imaging. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: China Scholarship Council, ESME-Sudria, EIT Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Quantification of aortic morphology plays an important role in the evaluation and follow‐up assessment of patients with aortic diseases, but often requires labor‐intensive and operator‐dependent measurements. Automatic solutions would help enhance their quality and reproducibility.

Purpose

To design a deep learning (DL)‐based automated approach for aortic landmarks and lumen detection derived from three‐dimensional (3D) MRI. Study Type Retrospective. Population Three hundred ninety‐one individuals (female: 47%, age = 51.9 ± 18.4) from three sites, including healthy subjects and patients (hypertension, aortic dilation, Turner syndrome), randomly divided into training/validation/test datasets (N = 236/77/78). Twenty‐five subjects were randomly selected and analyzed by three operators with different levels of expertise. Field Strength/Sequence 1.5‐T and 3‐T, 3D spoiled gradient‐recalled or steady‐state free precession sequences. Assessment Reinforcement learning and a two‐stage network trained using reference landmarks and segmentation from an existing semi‐automatic software were used for aortic landmark detection and segmentation from sinotubular junction to coeliac trunk. Aortic segments were defined using the detected landmarks while the aortic centerline was extracted from the segmentation and morphological indices (length, aortic diameter, and volume) were computed for both the reference and the proposed segmentations. Statistical Tests Segmentation: Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetrical surface distance (ASSD); landmark detection: Euclidian distance (ED); model robustness: Spearman correlation, Bland–Altman analysis, Kruskal–Wallis test for comparisons between reference and DL‐derived aortic indices; inter‐observer study: Williams index (WI). A WI 95% confidence interval (CI) lower bound >1 indicates that the method is within the inter‐observer variability. A P ‐value 0.95, mean bias

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningImaging, Three-DimensionalAortaMagnetic Resonance ImagingHumansFemaleMaleMiddle AgedRetrospective StudiesReproducibility of ResultsAdultAgedTurner SyndromeAortic DiseasesImage Processing, Computer-AssistedHypertensionImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

3D cardiac MRIaortadeep learningsegmentation

Autor:innen und Institutionen

  • Sorbonne Université, INSERM, CNRS, Laboratoire d'Imagerie Biomédicale (LIB), Paris, France.
  • Institute of Cardiometabolism and Nutrition (ICAN), Paris, France.
  • ESME Sudria Research Lab, Paris, France.
  • Université de Paris Cité, PARCC, INSERM, Paris, France.
  • Assistance Publique Hôpitaux de Paris, Hôpital Européen Georges Pompidou, Paris, France.
  • Imagerie Cardio-Thoracique (ICT), Sorbonne Université, AP-HP, Groupe Hospitalier Pitié-Salpêtrière, Paris, France.

ORCID-Profile: Jia Guo, Gilles Soulat, Elie Mousseaux, Thomas Dietenbeck

Förderung

  • China Scholarship Council
  • ESME-Sudria
  • EIT Health
  • Fondation pour la Recherche Médicale
  • Fondation de recherche sur l'hypertension arterielle

Zitieren

APA

Guo, J., Bouaou, K., Houriez-Gombaud-Saintonge, S., Gueda, M., Gencer, U., Nguyen, V., Charpentier, E., Soulat, G., Redheuil, A., Mousseaux, E., Kachenoura, N., & Dietenbeck, T. (2024). Deep Learning‐Based Analysis of Aortic Morphology From Three‐Dimensional MRI. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.29236

Vancouver

Guo J, Bouaou K, Houriez-Gombaud-Saintonge S, Gueda M, Gencer U, Nguyen V, et al. Deep Learning‐Based Analysis of Aortic Morphology From Three‐Dimensional MRI. Journal of Magnetic Resonance Imaging. 2024. doi:10.1002/jmri.29236

BibTeX
@article{Guo2024,
  author = {Guo, Jia and Bouaou, Kevin and Houriez-Gombaud-Saintonge, Sophia and Gueda, Moussa and Gencer, Umit and Nguyen, Vincent and Charpentier, Etienne and Soulat, Gilles and Redheuil, Alban and Mousseaux, Elie and Kachenoura, Nadjia and Dietenbeck, Thomas},
  title = {Deep Learning‐Based Analysis of Aortic Morphology From Three‐Dimensional MRI},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2024},
  doi = {10.1002/jmri.29236}
}
Kostenlos starten →