Deep Learning–Based Reconstruction Improves Image Quality in Canine Cranial Abdominal MRI: A Prospective Pilot Study
Veterinary Radiology & Ultrasound · 2026
DOI: 10.1111/vru.70193 ↗Kurz gefasst
Fachartikel in der Zeitschrift Veterinary Radiology & Ultrasound, 2026. Verfasst von Hyemin Na und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Veterinary Medicine, Kyungpook National University, Daegu, Republic of Korea. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Abdomen, Deep Learning, Image Processing, Computer-Assisted. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
The application of deep learning–based reconstruction (DLR) to magnetic resonance imaging (MRI) has been recently introduced in human and veterinary medicine to improve image quality without prolonging acquisition time. We hypothesized that cranial abdominal MRI with DLR would have superior image quality than conventional MRI. This prospective comparative pilot study aimed to compare cranial abdominal MR image quality with versus without DLR application in dogs. Transverse T2‐weighted and T1‐weighted images with and without contrast enhancement of the cranial abdomen region were performed in 10 clinically healthy dogs. The original and DLR images were generated from a single set of raw data using the DLR network embedded reconstruction pathway. The signal‐to‐noise ratio (SNR) and contrast‐to‐noise ratio (CNR) were calculated for quantitative analysis. Qualitative analysis included evaluation of the edge sharpness of the liver and pancreas, the conspicuity of the adrenal glands, respiratory motion artifacts, coarseness, and overall image quality using a 4‐point scale. Quantitative and qualitative values were compared between images with DLR and their counterparts. The mean SNR and CNR of all images with DLR were significantly higher than those of their counterparts ( p < 0.05). Qualitative analysis parameters, except for respiratory motion artifacts, were significantly superior in images with DLR compared with counterparts for all sequences ( p < 0.05). The present study demonstrated that cranial abdominal MRI with DLR is feasible to improve image quality without prolonging acquisition time.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Veterinary Medicine, Kyungpook National University, Daegu, Republic of Korea.
- College of Veterinary Medicine, Chungnam National University, Daejeon, Republic of Korea.
- Laboratory of Veterinary Radiology, Azabu University, Sagamihara, Kanagawa, Japan.
ORCID-Profile: Sang-Kwon Lee, Kazutaka Yamada, Kija Lee
Zitieren
APA
Na, H., Lee, S. K., Choi, H., Lee, Y., Yamada, K., & Lee, K. (2026). Deep Learning–Based Reconstruction Improves Image Quality in Canine Cranial Abdominal MRI: A Prospective Pilot Study. Veterinary Radiology & Ultrasound. https://doi.org/10.1111/vru.70193
Vancouver
Na H, Lee SK, Choi H, Lee Y, Yamada K, Lee K. Deep Learning–Based Reconstruction Improves Image Quality in Canine Cranial Abdominal MRI: A Prospective Pilot Study. Veterinary Radiology & Ultrasound. 2026. doi:10.1111/vru.70193
BibTeX
@article{Na2026,
author = {Na, Hyemin and Lee, Sang-Kwon and Choi, Hojung and Lee, Youngwon and Yamada, Kazutaka and Lee, Kija},
title = {Deep Learning–Based Reconstruction Improves Image Quality in Canine Cranial Abdominal MRI: A Prospective Pilot Study},
journal = {Veterinary Radiology & Ultrasound},
year = {2026},
doi = {10.1111/vru.70193}
}
EUVIMED