EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning‐Enabled Automated Quality Control for Liver MR Elastography: Initial Results

Heriberto A Nieves-Vazquez iD, Efe Ozkaya, Waiman Meinhold iD, Amine Geahchan, Octavia Bane iD, Jun Ueda, Bachir Taouli iD

Journal of Magnetic Resonance Imaging · 2025

DOI: 10.1002/jmri.29490 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2025. Verfasst von Heriberto A Nieves-Vazquez und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA. Hauptthemen laut MEDLINE: Deep Learning, Elasticity Imaging Techniques, Liver, Quality Control. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Several factors can impair image quality and reliability of liver magnetic resonance elastography (MRE), such as inadequate driver positioning, insufficient wave propagation and patient‐related factors.

Purpose

To report initial results on automatic classification of liver MRE image quality using various deep learning (DL) architectures. Study Type Retrospective, single center, IRB‐approved human study. Population Ninety patients (male = 51, mean age 52.8 ± 14.1 years). Field Strengths/Sequences 1.5 T and 3 T MRI , 2D GRE, and 2D SE ‐ EPI . Assessment The curated dataset was comprised of 914 slices obtained from 149 MRE exams in 90 patients. Two independent observers examined the confidence map overlaid elastograms (CMOEs) for liver stiffness measurement and assigned a quality score (non‐diagnostic vs. diagnostic) for each slice. Several DL architectures (ResNet18, ResNet34, ResNet50, SqueezeNet, and MobileNetV2) for binary quality classification of individual CMOE slice inputs were evaluated, using an 8‐fold stratified cross‐validation (800 slices) and a test dataset (114 slices). A majority vote ensemble combining the models' predictions of the highest‐performing architecture was evaluated. Statistical Test The inter‐observer agreement and the agreement between DL models and one observer were assessed using Cohen's unweighted Kappa coefficient. Accuracy, precision, and recall of the cross‐validation and the ensemble were calculated for the test dataset.

Results

The average accuracy across the eight models trained using each architecture ranged from 0.692 to 0.851 for the test dataset. The ensemble of the best performing architecture (SqueezeNet) yielded an accuracy of 0.921. The inter‐observer agreement was excellent (Kappa 0.896 [95% CI 0.845–0.947]). The agreement between observer 1 and the predictions of each SqueezeNet model was slight to almost perfect (Kappa range: 0.197–0.831) and almost perfect for the ensemble (Kappa: 0.833).

Conclusion

Our initial study demonstrates an automated DL‐based approach for classifying liver 2D MRE diagnostic quality with an average accuracy of 0.851 (range 0.675–0.921) across the SqueezeNet models. Evidence Level 4 Technical Efficacy Stage 1

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningElasticity Imaging TechniquesLiverQuality ControlMagnetic Resonance ImagingHumansMaleMiddle AgedFemaleRetrospective StudiesReproducibility of ResultsAdultAgedImage Processing, Computer-AssistedImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

deep learningimage quality controlliver stiffnessmagnetic resonance elastography

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA.
  • BioMedical Engineering and Imaging Institute, Icahn School of Medicine Mount Sinai, New York, New York, USA.
  • Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
  • School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA.

ORCID-Profile: Heriberto A Nieves-Vazquez, Waiman Meinhold, Octavia Bane, Bachir Taouli

Förderung

  • National Science Foundation
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Nieves-Vazquez, H. A., Ozkaya, E., Meinhold, W., Geahchan, A., Bane, O., Ueda, J., & Taouli, B. (2025). Deep Learning‐Enabled Automated Quality Control for Liver MR Elastography: Initial Results. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.29490

Vancouver

Nieves-Vazquez HA, Ozkaya E, Meinhold W, Geahchan A, Bane O, Ueda J, et al. Deep Learning‐Enabled Automated Quality Control for Liver MR Elastography: Initial Results. Journal of Magnetic Resonance Imaging. 2025. doi:10.1002/jmri.29490

BibTeX
@article{NievesVazquez2025,
  author = {Nieves-Vazquez, Heriberto A and Ozkaya, Efe and Meinhold, Waiman and Geahchan, Amine and Bane, Octavia and Ueda, Jun and Taouli, Bachir},
  title = {Deep Learning‐Enabled Automated Quality Control for Liver MR Elastography: Initial Results},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2025},
  doi = {10.1002/jmri.29490}
}
Kostenlos starten →