Deep learning-based image reconstruction significantly improves image quality of MRI examinations of the orbit at 3 Tesla - 23/11/25

Doi : 10.1016/j.diii.2025.11.003

Aurore Sajust de Bergues de Escalup ^a,^{^{1
These authors contributed equally.},}^⁎ , Augustin Lecler ^a,^b,^{^{1
These authors contributed equally.}}, Émilie Poirion ^a, Caroline Papeix ^c, Romain Deschamps ^c, Dan Milea ^d, Julien Savatovsky ^a, Loïc Duron ^a, Emma O’Shaughnessy ^a
^a Department of Neuroradiology, Hôpital Fondation Adolphe de Rothschild, 75019 Paris, France
^b Université Paris Cité, Faculté de Médecine, 75006 Paris, France
^c Department of Neurology, Hôpital Fondation Adolphe de Rothschild, 75019 Paris, France
^d Department of Neuro-Ophthalmology, Hôpital Fondation Adolphe de Rothschild, 75019 Paris, France

^⁎Corresponding author.

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Sunday 23 November 2025

Highlights

•	Deep learning-based image reconstruction significantly increases signal-to-noise ratio and contrast-to-noise ratio of coronal T2-weighted MR images of the orbit obtained at 3 Tesla.
•	Deep learning-based image reconstruction improves optic nerve sharpness, brain sharpness and overall image quality of coronal T2-weighted and post-contrast fat-saturated T1-weighted MR images obtained at 3 Tesla.
•	Diagnostic findings, including optic nerve hypersignal, enhancement, atrophy and orbital meningiomas, are preserved on both T2-weighted and post-contrast T1-weighted MR images obtained with deep learning-based reconstruction.

Le texte complet de cet article est disponible en PDF.

Abstract

Purpose

The purpose of this study was to assess the benefit of a deep learning-based image reconstruction (DLBIR) for improving image quality in orbital magnetic resonance imaging (MRI) at 3 Tesla (T).

Materials and methods

Seventy-one patients (48 women and 23 men) with a mean age of 52 ± 19.5 (standard deviation [SD]) years (age range: 7–90 years) who underwent MRI examination of the orbit at 3 T between January and June of 2024, were included in the study. Coronal T2-weighted MR images obtained in 70 patients and post-contrast fat-saturated (FS) coronal T1-weighted MR images obtained in 25 patients, were reconstructed with and without DLBIR, resulting in four imaging sets. Two radiologists independently and blindly measured the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the optic nerves on the four imaging sets. Image quality and orbital abnormalities were assessed using a standardized 5-point Likert scale. Comparisons between MR images obtained with and without DLBIR were performed using Wilcoxon test for ordinal and quantitative variables and McNemar test for paired binary data.

Results

SNR and CNR of coronal T2-weighted MR images were significantly greater using DLBIR (26.67 ± 9.03 [SD], and 14.87 ± 10.31 [SD], respectively) than without DLBIR (18.91 ± 7.28 [SD], and 9.78 ± 8.47 [SD], respectively) (P < 0.001). There were no differences in SNR and CNR between post-contrast FS T1-weighted images obtained with DLBIR (85.56 ± 63.13 [SD], and 64 ± 41.38 [SD], respectively) and those obtained without DLBIR (91.36 ± 48.49 [SD], and 43.25 ± 20.4 [SD], respectively) (P = 0.35, and P = 0.14, respectively). Qualitatively, good-to-excellent image quality was obtained more frequently with DLBIR than without DLBIR for T2-weighted and post-contrast FS T1-weighted images with respect to optic nerve sharpness (67 % vs. 16 %, and 8 % vs. 0 %, respectively), brain sharpness (90 % vs. 6 %, and 68 % vs. 4 %, respectively), and overall image quality (73 % vs. 1 % and 36 % vs. 0 %, respectively) (all P ≤ 0.001). No significant differences in the detection rates of orbital abnormalities were found between MR images obtained with and without DLBIR, including optic nerve hyperintensity (34 % vs. 31 %, respectively; P = 0.16) and optic nerve atrophy (33 % for both) on T2-weighted images, and optic nerve enhancement on post-contrast FS T1-weighted images (16 % for both).