Skip to main content
Top

08-06-2024 | Magnetic Resonance Imaging | Technical Note

Verification of image quality improvement by deep learning reconstruction to 1.5 T MRI in T2-weighted images of the prostate gland

Authors: Yoshiomi Sato, Kiyoshi Ohkuma

Published in: Radiological Physics and Technology

Login to get access

Abstract

This study aimed to evaluate whether the image quality of 1.5 T magnetic resonance imaging (MRI) of the prostate is equal to or higher than that of 3 T MRI by applying deep learning reconstruction (DLR). To objectively analyze the images from the 13 healthy volunteers, we measured the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the images obtained by the 1.5 T scanner with and without DLR, as well as for images obtained by the 3 T scanner. In the subjective, T2W images of the prostate were visually evaluated by two board-certified radiologists. The SNRs and CNRs in 1.5 T images with DLR were higher than that in 3 T images. Subjective image scores were better for 1.5 T images with DLR than 3 T images. The use of the DLR technique in 1.5 T MRI substantially improved the SNR and image quality of T2W images of the prostate gland, as compared to 3 T MRI.
Literature
4.
go back to reference Kaji Y, Kuroda K, Maeda T, Kitamura Y, Fujiwara T, Matsuoka Y, Tamura M, Takei N, Matsuda T, Sugimura K. Anatomical and metabolic assessment of prostate using a 3-Tesla MR scanner with a custom-made external transceive coil: healthy volunteer study. J Magn Reson Imaging. 2007;25(3):517–26. https://doi.org/10.1002/jmri.20829.CrossRefPubMed Kaji Y, Kuroda K, Maeda T, Kitamura Y, Fujiwara T, Matsuoka Y, Tamura M, Takei N, Matsuda T, Sugimura K. Anatomical and metabolic assessment of prostate using a 3-Tesla MR scanner with a custom-made external transceive coil: healthy volunteer study. J Magn Reson Imaging. 2007;25(3):517–26. https://​doi.​org/​10.​1002/​jmri.​20829.CrossRefPubMed
7.
go back to reference PI-RADS (2019) Prostate imaging reporting and data system version 2.1. Am Coll Radiol PI-RADS (2019) Prostate imaging reporting and data system version 2.1. Am Coll Radiol
11.
go back to reference Jerrolds J, Keene S. MRI safety at 3 T versus 1.5 T. Internet J World Health Soc Polit. 2009;6(1). Jerrolds J, Keene S. MRI safety at 3 T versus 1.5 T. Internet J World Health Soc Polit. 2009;6(1).
32.
go back to reference Zhang J, Tian W-Z, Hu C-H, et al. Age-related changes of normal prostate: evaluation by MR diffusion tensor imaging. Int J Clin Exp Med. 2015;8(7):11220–4.PubMedPubMedCentral Zhang J, Tian W-Z, Hu C-H, et al. Age-related changes of normal prostate: evaluation by MR diffusion tensor imaging. Int J Clin Exp Med. 2015;8(7):11220–4.PubMedPubMedCentral
Metadata
Title
Verification of image quality improvement by deep learning reconstruction to 1.5 T MRI in T2-weighted images of the prostate gland
Authors
Yoshiomi Sato
Kiyoshi Ohkuma
Publication date
08-06-2024
Publisher
Springer Nature Singapore
Published in
Radiological Physics and Technology
Print ISSN: 1865-0333
Electronic ISSN: 1865-0341
DOI
https://doi.org/10.1007/s12194-024-00819-5