Enhanced muscle MRI using deep learning: shorter acquisition time with improved image quality
PeerJ · 19.03.2026 · 14 · e21012
DOI: 10.7717/peerj.21012 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ, online erschienen am 19.03.2026. Verfasst von Peilin Fan und 10 weiteren Autor:innen. Beteiligte Einrichtung: Radiology, Peking Union Medical College Hospital, Beijing, China. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Muscle, Skeletal, Image Processing, Computer-Assisted. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National High Level Hospital Clinical Research Funding, CAMS Innovation Fund for Medical Sciences.
Abstract (Originalsprache)
Background
This study aimed to evaluate the effectiveness of a k-space learning type deep learning (DL) reconstruction combined with fat-suppressed turbo spin-echo (TSE) T2-weighted imaging (T2WI) in improving image quality and reducing acquisition time for muscle magnetic resonance imaging (MRI).
Methods
In this prospective study, 98 controls (mean age 56.3 years) and 33 patients (mean age 45.2 years) underwent both DL reconstructed TSE (TSE DL ) and standard fat-suppressed TSE T2WI scans of the bilateral thigh using a 3T MRI scanner. Quantitative metrics, including noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR), were measured. Two radiologists performed qualitative assessments using a 5-point Likert scale to evaluate image quality, anatomical structure visibility, and diagnostic confidence. Inter-reader agreement and statistical comparisons between groups were analyzed.
Results
The acquisition times were 2 min 11s and 1 min 33s for standard TSE and TSE DL , respectively. TSE DL demonstrated significantly lower noise and higher SNR and CNR than standard TSE in both healthy volunteers and patients ( p < 0.05). Qualitative assessments showed that TSE DL provided superior overall image quality, better visualization of thigh muscles and femoral bones, sharper edges, improved contrast resolution, and higher diagnostic confidence compared to standard TSE ( p < 0.01).
Conclusion
DL during image acquisition reconstruction, combined with fat-suppressed TSE T2WI, significantly enhances image quality and reduces acquisition time in muscle MRI, suggesting its potential for routine clinical use in musculoskeletal imaging.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Radiology, Peking Union Medical College Hospital, Beijing, China.
- MR Application Predevelopment, Siemens Healthineers AG, Forchheim, Germany.
- MR Research Collaboration, Siemens Healthineers Ltd, Beijing, China.
- Neurology, Peking Union Medical College Hospital, Beijing, China.
- Rheumatology and Immunology, Peking Union Medical College Hospital, Beijing, China.
ORCID-Profile: Feng Feng
Förderung
- National High Level Hospital Clinical Research Funding
- CAMS Innovation Fund for Medical Sciences
Zitieren
APA
Fan, P., Zhang, Z., Hou, B., Liu, D., Nickel, M. D., Zhu, J., Dai, Y., Wang, Q., Wang, F., Yu, W., & Feng, F. (2026). Enhanced muscle MRI using deep learning: shorter acquisition time with improved image quality. PeerJ, 14, e21012. https://doi.org/10.7717/peerj.21012
Vancouver
Fan P, Zhang Z, Hou B, Liu D, Nickel MD, Zhu J, et al. Enhanced muscle MRI using deep learning: shorter acquisition time with improved image quality. PeerJ. 2026;14:e21012. doi:10.7717/peerj.21012
BibTeX
@article{Fan2026,
author = {Fan, Peilin and Zhang, Zaizhu and Hou, Bo and Liu, Dong and Nickel, Marcel Dominik and Zhu, Jinxia and Dai, Yi and Wang, Qian and Wang, Fengdan and Yu, Wei and Feng, Feng},
title = {Enhanced muscle MRI using deep learning: shorter acquisition time with improved image quality},
journal = {PeerJ},
year = {2026},
volume = {14},
pages = {e21012},
doi = {10.7717/peerj.21012}
}
EUVIMED