• Application of deep learning r...

Treffer: Application of deep learning reconstruction in abdominal magnetic resonance cholangiopancreatography for image quality improvement and acquisition time reduction.

Title:
Application of deep learning reconstruction in abdominal magnetic resonance cholangiopancreatography for image quality improvement and acquisition time reduction.
Authors:
Chen PT; Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan; Department of Medical Imaging, National Taiwan University Cancer Center and National Taiwan University College of Medicine, Taipei, Taiwan; Department of Medical Imaging, National Taiwan University Hospital Hsinchu Branch, Hsinchu, Taiwan., Yeh CY; Department of Medical Imaging, National Taiwan University Cancer Center and National Taiwan University College of Medicine, Taipei, Taiwan., Chang YC; Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan; Department of Medical Imaging, National Taiwan University Cancer Center and National Taiwan University College of Medicine, Taipei, Taiwan; Department of Medical Imaging, National Taiwan University Hospital Hsinchu Branch, Hsinchu, Taiwan., Chen P; Internal Medicine, Chicago Medical School Internal Medicine Residency Program at Northwestern Mchenry Hospital, McHenry, USA., Lee CW; GE Healthcare, Taipei, Taiwan., Shieh CC; GE Healthcare, Taipei, Taiwan., Lin CY; GE Healthcare, Taipei, Taiwan., Liu KL; Department of Medical Imaging, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan; Department of Medical Imaging, National Taiwan University Cancer Center and National Taiwan University College of Medicine, Taipei, Taiwan. Electronic address: kaolangliu@gmail.com.
Source:
Journal of the Formosan Medical Association = Taiwan yi zhi [J Formos Med Assoc] 2025 Dec; Vol. 124 (12), pp. 1141-1148. Date of Electronic Publication: 2024 Oct 25.
Publication Type:
Journal Article; Comparative Study
Language:
English
Journal Info:
Publisher: Formosan Medical Association, Elsevier Country of Publication: Singapore NLM ID: 9214933 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 0929-6646 (Print) Linking ISSN: 09296646 NLM ISO Abbreviation: J Formos Med Assoc Subsets: MEDLINE
Imprint Name(s):
Publication: 2003- : Singapore : Formosan Medical Association, Elsevier
Original Publication: Taipei, Taiwan : Formosan Medical Association, [1991-
MeSH Terms:
Deep Learning* , Quality Improvement* , Abdomen*/diagnostic imaging , Cholangiopancreatography, Magnetic Resonance*/methods , Image Processing, Computer-Assisted*/methods, Humans ; Male ; Female ; Middle Aged ; Retrospective Studies ; Aged ; Signal-To-Noise Ratio ; Adult ; Time Factors
Contributed Indexing:
Keywords: Computer-assisted; Deep learning; Image processing; Magnetic resonance imaging
Entry Date(s):
Date Created: 20241025 Date Completed: 20251124 Latest Revision: 20251124
Update Code:
20251125
DOI:
10.1016/j.jfma.2024.10.017
PMID:
39455401
Database:
MEDLINE

Weitere Informationen

Purpose: To compare deep learning (DL)-based and conventional reconstruction through subjective and objective analysis and ascertain whether DL-based reconstruction improves the quality and acquisition speed of clinical abdominal magnetic resonance imaging (MRI).
Methods: The 124 patients who underwent abdominal MRI between January and July 2021 were retrospectively studied. For each patient, two-dimensional axial T <subscript>2</subscript> -weighted single-shot fast spin-echo MRI images with or without fat saturation were reconstructed using DL-based and conventional methods. The subjective image quality scores and objective metrics, including signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) of the images were analysed. An explorative analysis was performed to compare 20 patients' MRI images with site routine settings, high-resolution settings and high-speed settings. Paired t tests and Wilcoxon signed-rank tests were used for subjective and objective comparisons.
Results: A total of 144 patients were evaluated (mean age, 62.2 ± 14.1 years; 83 men). The MRI images reconstructed using DL-based methods had higher SNRs and CNRs than did those reconstructed using conventional methods (all p < 0.01). The subjective scores of the images reconstructed using DL-based methods were higher than those of the images reconstructed using conventional methods (p < 0.01), with significantly lower variation (p < 0.01). Exploratory analysis revealed that the DL-based reconstructions with thin slice thickness and higher temporal resolution had the highest image quality and were associated with the shortest scan times.
Conclusion: DL-based reconstruction methods can be used to improve the quality with higher stability and accelerate the acquisition of abdominal MRI.
(Copyright © 2025 Formosan Medical Association. Published by Elsevier B.V. All rights reserved.)

Declaration of competing interest The authors of this manuscript declare relationships with the following companies: GE healthcare, Taiwan. Three co-authors, C.-W. Lee, C.-C. Shieh and C.-Y. Lin, are employees of GE Healthcare, Taiwan, and they provided sequence information and technical support. No funding was received from GE Healthcare for publication activities.