EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Incorporating Radiologist Knowledge Into MRI Quality Metrics for Machine Learning Using Rank‐Based Ratings

Chenwei Tang iD, Laura B Eisenmenger, Leonardo Rivera-Rivera iD, Eugene Huo, Jacqueline C Junn, Anthony D Kuner, Thekla H Oechtering, Anthony Peret, Jitka Starekova iD, Kevin M Johnson

Journal of Magnetic Resonance Imaging · 2025

DOI: 10.1002/jmri.29672 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2025. Verfasst von Chenwei Tang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Radiologists, Machine Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIA NIH HHS, NINDS NIH HHS, Deutsche Forschungsgemeinschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Deep learning (DL) often requires an image quality metric; however, widely used metrics are not designed for medical images.

Purpose

To develop an image quality metric that is specific to MRI using radiologists image rankings and DL models. Study Type Retrospective. Population A total of 19,344 rankings on 2916 unique image pairs from the NYU fastMRI Initiative neuro database was used for the neural network‐based image quality metrics training with an 80%/20% training/validation split and fivefold cross‐validation. Field Strength/Sequence 1.5 T and 3 T T1, T1 postcontrast, T2, and FLuid Attenuated Inversion Recovery (FLAIR). Assessment Synthetically corrupted image pairs were ranked by radiologists ( N = 7), with a subset also scoring images using a Likert scale ( N = 2). DL models were trained to match rankings using two architectures (EfficientNet and IQ‐Net) with and without reference image subtraction and compared to ranking based on mean squared error (MSE) and structural similarity (SSIM). Image quality assessing DL models were evaluated as alternatives to MSE and SSIM as optimization targets for DL denoising and reconstruction. Statistical Tests Radiologists' agreement was assessed by a percentage metric and quadratic weighted Cohen's kappa. Ranking accuracies were compared using repeated measurements analysis of variance. Reconstruction models trained with IQ‐Net score, MSE and SSIM were compared by paired t test. P < 0.05 was considered significant.

Results

Compared to direct Likert scoring, ranking produced a higher level of agreement between radiologists (70.4% vs. 25%). Image ranking was subjective with a high level of intraobserver agreement () and lower interobserver agreement (). IQ‐Net and EfficientNet accurately predicted rankings with a reference image ( and ). However, EfficientNet resulted in images with artifacts and high MSE when used in denoising tasks while IQ‐Net optimized networks performed well for both denoising and reconstruction tasks. Data Conclusion Image quality networks can be trained from image ranking and used to optimize DL tasks. Level of Evidence 3 Technical Efficacy Stage 1

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingRadiologistsMachine LearningImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedHumansRetrospective StudiesDeep LearningNeural Networks, ComputerReproducibility of ResultsBrainDatabases, FactualAlgorithms

Stichwörter der Autor:innen

deep learningimage quality metricsimage reconstruction

Autor:innen und Institutionen

  • Department of Medical Physics, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA.
  • Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA.
  • Department of Medicine, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA.
  • Department of Radiology, University of California, San Francisco, California, USA.
  • Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
  • Department of Radiology and Nuclear Medicine, Universität zu Lübeck, Lübeck, Germany.

ORCID-Profile: Chenwei Tang, Leonardo Rivera-Rivera, Jitka Starekova

Förderung

  • NIA NIH HHS
  • NINDS NIH HHS
  • Deutsche Forschungsgemeinschaft
  • National Institute of Neurological Disorders and Stroke
  • National Institute on Aging

Zitieren

APA

Tang, C., Eisenmenger, L. B., Rivera-Rivera, L., Huo, E., Junn, J. C., Kuner, A. D., Oechtering, T. H., Peret, A., Starekova, J., & Johnson, K. M. (2025). Incorporating Radiologist Knowledge Into MRI Quality Metrics for Machine Learning Using Rank‐Based Ratings. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.29672

Vancouver

Tang C, Eisenmenger LB, Rivera-Rivera L, Huo E, Junn JC, Kuner AD, et al. Incorporating Radiologist Knowledge Into MRI Quality Metrics for Machine Learning Using Rank‐Based Ratings. Journal of Magnetic Resonance Imaging. 2025. doi:10.1002/jmri.29672

BibTeX
@article{Tang2025,
  author = {Tang, Chenwei and Eisenmenger, Laura B and Rivera-Rivera, Leonardo and Huo, Eugene and Junn, Jacqueline C and Kuner, Anthony D and Oechtering, Thekla H and Peret, Anthony and Starekova, Jitka and Johnson, Kevin M},
  title = {Incorporating Radiologist Knowledge Into MRI Quality Metrics for Machine Learning Using Rank‐Based Ratings},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2025},
  doi = {10.1002/jmri.29672}
}
Kostenlos starten →