Feasibility of virtual T2-weighted fat-saturated breast MRI images by convolutional neural networks

Liebert A, Hadler D, Ehring C, Schreiter H, Brock L, Kapsner L, Eberle J, Erber R, Emons J, Laun FB, Uder M, Wenkel E, Ohlmeyer S, Bickelhaupt S (2025)

Publication Language: English

Publication Type: Journal article

Publication year: 2025

Journal

European Radiology Experimental European Society of Radiology

Book Volume: 9

Article Number: 47

Journal Issue: 1

DOI: 10.1186/s41747-025-00580-3

Abstract

Background: Breast magnetic resonance imaging (MRI) protocols often include T2-weighted fat-saturated (T2w-FS) sequences, which support tissue characterization but significantly increase scan time. This study aims to evaluate whether a 2D-U-Net neural network can generate virtual T2w-FS (VirtuT2w) images from routine multiparametric breast MRI images. Methods: This IRB-approved, retrospective study included 914 breast MRI examinations from January 2017 to June 2020. The dataset was divided into training (n = 665), validation (n = 74), and test sets (n = 175). The U-Net was trained using different input protocols consisting of T1-weighted, diffusion-weighted, and dynamic contrast-enhanced sequences to generate VirtuT2. Quantitative metrics were used to evaluate the different input protocols. A qualitative assessment by two radiologists was used to evaluate the VirtuT2w images of the best input protocol. Results: VirtuT2w images demonstrated the best quantitative metrics compared to original T2w-FS images for an input protocol using all of the available data. A high level of high-frequency error norm (0.87) indicated a strong blurring presence in the VirtuT2 images, which was also confirmed by qualitative reading. Radiologists correctly identified VirtuT2 images with at least 96% accuracy. Significant difference in diagnostic image quality was noted for both readers (p ≤ 0.015). Moderate inter-reader agreement was observed for edema detection on both T2w-FS images (κ = 0.49) and VirtuT2 images (κ = 0.44). Conclusion: The 2D-U-Net generated virtual T2w-FS images similar to real T2w-FS images, though blurring remains a limitation. Investigation of other architectures and using larger datasets is necessary to improve potential future clinical applicability. Relevance statement: Generating VirtuT2 images could potentially decrease the examination time of multiparametric breast MRI, but its quality needs to improve before introduction into a clinical setting. Key Points: Breast MRI T2w-fat-saturated (FS) images can be virtually generated using convolutional neural networks. Image blurring in virtual T2w-FS images currently limits their clinical applicability. Best quantitative performance could be achieved when using full dynamic-contrast-enhanced acquisition and DWI as input of the neural network.

Authors with CRIS profile

Andrzej Liebert Institute of Radiology Dominique Hadler Institute of Radiology Hannes Schreiter Institute of Radiology Luise Brock Institute of Radiology Lorenz Kapsner Institute of Radiology Jessica Eberle Institute of Radiology Julius Emons Department of Obstetrics and Gynaecology Frederik Bernd Laun Professur für quantitative MR-Bildgebung Michael Uder Lehrstuhl für Diagnostische Radiologie Evelyn Wenkel Medizinische Fakultät Sabine Ohlmeyer Institute of Radiology Sebastian Bickelhaupt Institute of Radiology

Involved external institutions

Universität Regensburg DE Germany (DE)

How to cite

APA:

Liebert, A., Hadler, D., Ehring, C., Schreiter, H., Brock, L., Kapsner, L.,... Bickelhaupt, S. (2025). Feasibility of virtual T2-weighted fat-saturated breast MRI images by convolutional neural networks. European Radiology Experimental, 9(1). https://doi.org/10.1186/s41747-025-00580-3

MLA:

Liebert, Andrzej, et al. "Feasibility of virtual T2-weighted fat-saturated breast MRI images by convolutional neural networks." European Radiology Experimental 9.1 (2025).

BibTeX: Download