Faster Acquisition and Improved Image Quality of T2-Weighted Dixon Breast MRI at 3T Using Deep Learning - A Prospective Study

Q: What was the main objective of the study?

To compare image quality features and lesion characteristics between a faster deep learning reconstructed T2-w fast spin-echo Dixon sequence and a conventional T2-w Dixon sequence for breast MRI.

Q: How were the quantitative and qualitative evaluations performed?

Quantitative assessment used ROI measurements of SNR and CNR, while qualitative assessment used independent Likert-scale ratings by two radiologists for image quality features, morphology, and diagnostic confidence.

Q: What were the key findings for acquisition time and image quality?

Acquisition time was 110 s for T2DL versus 266 s for T2STD, and SNR/CNR and multiple image quality scores were significantly higher with T2DL, with fewer artifacts and overall better diagnostic confidence for cysts.

Sep 23, 2026

Uploaded by Logic

A prospective study evaluated how a faster deep learning (DL) reconstruction for T2-weighted (T2-w) fast spin-echo (FSE) Dixon breast MRI compares with a conventional T2-w FSE Dixon sequence. Using a 3T scanner, both T2DL and T2STD were acquired per patient and assessed quantitatively via ROI-based signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and qualitatively by two radiologists using Likert scoring for image quality, morphology, and diagnostic confidence for cysts and breast cancers. Results in 140 analyzed women showed shorter acquisition time, higher SNR/CNR, fewer artifacts, higher image quality scores, and reader preference for T2DL.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Materials and Methods

Results

Conclusion

Original Article | Breast Imaging eISSN 2005-8330 [https://doi.org/10.3348/kjr.2023.1303](https://doi.org/10.3348/kjr.2023.1303) [Korean J Radiol 2025](Korean J Radiol 2025);[26](26)([1](1))[:29-42](:29-42) Faster Acquisition and Improved Image Quality of T2-Weighted Dixon Breast MRI at 3T Using Deep Learning: A Prospective Study Caroline Wilpert1, Hannah Schneider1, Alexander Rau1,2, Maximilian Frederic Russe1, Benedict Oerther1, Ralph Strecker3,4, Marcel Dominic Nickel3, Elisabeth Weiland3, Alexa Haeger5,6, Matthias Benndorf1, Thomas Mayrhofer7,8, Jakob Weiss1, Fabian Bamberg1, Marisa Windfuhr-Blum1, Jakob Neubauer1 1 Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany 2 Department of Neuroradiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany 3MR Application Predevelopment, Siemens Healthcare GmbH, Erlangen, Germany 4 EMEA Scientific Partnerships, Siemens Healthcare GmbH, Erlangen, Germany 5 Department of Neurology, RWTH Aachen University, Aachen, Germany 6JARA-BRAIN Institute Molecular Neuroscience and Neuroimaging, Forschungszentrum Jülich GmbH and RWTH Aachen University, Aachen, Germany 7School of Business Studies, Stralsund University of Applied Sciences, Stralsund, Germany 8Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA Objective: The aim of this study was to compare image quality features and lesion characteristics between a faster deep learning (DL) reconstructed T2-weighted (T2-w) fast spin-echo (FSE) Dixon sequence with super-resolution (T2DL) and a conventional T2-w FSE Dixon sequence (T2STD) for breast magnetic resonance imaging (MRI) . Materials and Methods: This prospective study was conducted between November 2022 and April 2023 using a 3T scanner. Both T2DL and T2STD sequences were acquired for each patient. Quantitative analysis was based on region-of-interest (ROI) measurements of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) . Qualitative analysis was performed independently by two radiologists using Likert scales to evaluate various image quality features, morphology, and diagnostic confidence for cysts and breast cancers. Reader preference between T2DL and T2STD was assessed via side-by-side comparison, and inter-reader reliability was also analyzed. Results: Total of 151 women were enrolled, with 140 women (mean age: 52 ± 14 years; 85 cysts and 31 breast cancers) included in the final analysis. The acquisition time was 110 s ± 0 for T2DL compared to 266 s ± 0 for T2STD. SNR and CNR were significantly higher in T2DL (P < 0.001) . T2DL was associated with higher image quality scores, reduced noise, and fewer artifacts (P < 0.001) . All evaluated anatomical regions (breast and axilla), breast implants, and bone margins were rated higher in T2DL (P ≤ 0.008), except for bone marrow, which scored higher in T2STD (P < 0.001). Scores for conspicuity, sharpness/ margins, and microstructure of cysts and breast cancers were higher in T2DL (P ≤ 0.002). Diagnostic confidence for cysts was improved with T2DL (P < 0.001). Readers significantly preferred T2DL over T2STD in side-by-side comparisons (P < 0.001). Conclusion: T2DL effectively corrected for SNR loss caused by accelerated image acquisition and provided a 58% reduction in acquisition time compared to T2STD. This led to fewer artifacts and improved overall image quality. Thus, T2DL is feasible and has the potential to replace conventional T2-w sequences for breast MRI examinations. Keywords: MRI methods; Artificial neural network/machine learning; Breast; Quality assurance/control and improvement; Cancer Received: December 29, 2023 Revised: October 15, 2024 Accepted: October 15, 2024 Corresponding author: Caroline Wilpert, MD, Department of Diagnostic and Interventi

FAQs

What was the main objective of the study?

To compare image quality features and lesion characteristics between a faster deep learning reconstructed T2-w fast spin-echo Dixon sequence and a conventional T2-w Dixon sequence for breast MRI.

How were the quantitative and qualitative evaluations performed?

Quantitative assessment used ROI measurements of SNR and CNR, while qualitative assessment used independent Likert-scale ratings by two radiologists for image quality features, morphology, and diagnostic confidence.

What were the key findings for acquisition time and image quality?

Acquisition time was 110 s for T2DL versus 266 s for T2STD, and SNR/CNR and multiple image quality scores were significantly higher with T2DL, with fewer artifacts and overall better diagnostic confidence for cysts.

Sep 23, 2026

Uploaded by Logic