EUVIMEDEUVIMED entdecken
Crossref

Feasibility of two-dimensional multi-segmented late gadolinium enhancement combined with artificial intelligence reconstruction deep-learning noise reduction in patients with non-ischemic cardiomyopathy

Makoto Orii, Jumpei Fujiwara, Jun Obara, Tsuyoshi Sugawara, Kunihiro Yoshioka

Magnetic Resonance Imaging · 2026

DOI: 10.1016/j.mri.2026.110642 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2026. Verfasst von Makoto Orii und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Iwate Medical University, Yahaba, Japan. Electronic address: kori931@gmail.com. Hauptthemen laut MEDLINE: Cardiomyopathies, Gadolinium, Deep Learning, Image Enhancement. Die Arbeit nennt 23 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: Although two-dimensional (2D) single-segmented late gadolinium enhancement (2D-SSLGE) sequences are the gold standard for LGE acquisition, 2D multi-segmented LGE (2D-MSLGE) and artificial intelligence reconstruction deep-learning noise reduction (NR) show a potential to improve image quality and reduce scan times. Thus, this study aimed to assess the feasibility of 2D-MSLGE reconstructed with NR in patients with non-ischemic cardiomyopathy (NICM). MATERIAL AND METHODS: This study prospectively enrolled 60 patients (39 men, mean age, 57.7 ± 16.5 years) with NICM. Subjective overall image quality was evaluated using a 5-point Likert scale. Artifact visibility was also scored. LGE mass was manually quantified using a semi-automated grayscale threshold with a cutoff value of 5 standard deviations. RESULTS: The median actual acquisition time of 2D-MSLGE reconstructed with NR (123 s; range, 81-246) was significantly shorter than that of 2D-SSLGE reconstructed with NR (540 s; range, 420-720 s, p < 0.001). There was no significant difference in overall image quality between 2D-MSLGE reconstructed with NR and 2D-SSLGE reconstructed with NR (median, 3.0; IQR, 3.0-3.0 vs. 3.0; IQR, 3.0-4.0, p = 0.197). Image noise was significantly reduced in 2D-MSLGE reconstructed with NR (3.0; 3.0-4.0) compared with that in 2D-SSLGE reconstructed with NR (3.0; 2.0-4.0, p = 0.026). No significant difference was found in the LGE mass between 2D-MSLGE reconstructed with NR (16.9%; 10.9-25.1) and 2D-SSLGE reconstructed with NR (17.3%; 11.4-27.0, p = 0.939). CONCLUSIONS: 2D-MSLGE images reconstructed with NR could be acquired at shorter scan times and provide accurate LGE in patients with NICM.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CardiomyopathiesGadoliniumDeep LearningImage EnhancementImage Processing, Computer-AssistedArtificial IntelligenceMagnetic Resonance ImagingHumansFemaleMaleMiddle AgedFeasibility StudiesContrast MediaProspective StudiesAgedAdultArtifactsSignal-To-Noise RatioImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

Image qualityLate gadolinium enhancementNoise reductionNon-ischemic cardiomyopathy

Substanzen

Contrast MediaGadolinium

Autor:innen und Institutionen

  • Department of Radiology, Iwate Medical University, Yahaba, Japan. Electronic address: kori931@gmail.com.
  • Department of Radiology, Iwate Medical University, Yahaba, Japan.
  • Department of Radiology Service, Iwate Medical University, Yahaba, Japan.

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Orii, M., Fujiwara, J., Obara, J., Sugawara, T., & Yoshioka, K. (2026). Feasibility of two-dimensional multi-segmented late gadolinium enhancement combined with artificial intelligence reconstruction deep-learning noise reduction in patients with non-ischemic cardiomyopathy. Magnetic Resonance Imaging. https://doi.org/10.1016/j.mri.2026.110642

Vancouver

Orii M, Fujiwara J, Obara J, Sugawara T, Yoshioka K. Feasibility of two-dimensional multi-segmented late gadolinium enhancement combined with artificial intelligence reconstruction deep-learning noise reduction in patients with non-ischemic cardiomyopathy. Magnetic Resonance Imaging. 2026. doi:10.1016/j.mri.2026.110642

BibTeX
@article{Orii2026,
  author = {Orii, Makoto and Fujiwara, Jumpei and Obara, Jun and Sugawara, Tsuyoshi and Yoshioka, Kunihiro},
  title = {Feasibility of two-dimensional multi-segmented late gadolinium enhancement combined with artificial intelligence reconstruction deep-learning noise reduction in patients with non-ischemic cardiomyopathy},
  journal = {Magnetic Resonance Imaging},
  year = {2026},
  doi = {10.1016/j.mri.2026.110642}
}
Kostenlos starten →