Deep Learning HASTE for Upper Abdominal MRI: Improved Image Quality, Speed, and Energy Efficiency in a Prospective Study
NMR in Biomedicine · 2026
DOI: 10.1002/nbm.70183 ↗Kurz gefasst
Fachartikel in der Zeitschrift NMR in Biomedicine, 2026. Verfasst von Jennifer Gotta und 24 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Goethe University Hospital Frankfurt, Frankfurt am Main, Germany. Hauptthemen laut MEDLINE: Deep Learning, Abdomen, Magnetic Resonance Imaging. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wilhelm Vaillant Stiftung.
Abstract (Originalsprache)
This prospective study aimed to perform a qualitative and quantitative comparison of deep learning (DL) and conventional T2‐weighted Half‐Fourier Acquisition Single‐shot Turbo spin Echo (HASTE) sequences for 3T MRI acquisition of the upper abdomen. From January 2024 to April 2024, 166 patients (60 ± 14 years) scheduled for MRI of the upper abdomen were prospectively enrolled. Each patient underwent two MRI examinations: one using a conventional T2‐weighted HASTE sequence, followed by a fast T2‐weighted HASTE sequence reconstructed with DL. Image quality, anatomical structure visualization, and diagnostic performance were independently assessed by three readers using a 5‐point Likert scale. Quantitative analysis included measurements of signal‐to‐noise ratio (SNR) and contrast‐to‐noise ratio (CNR) for both sequences. Additionally, radiomic features were extracted and analyzed for significant variations. Interreader agreement was evaluated using Fleiss' Kappa. The DL HASTE sequence showed significantly superior overall image quality ( p < 0.001), fewer artifacts ( p < 0.001), and improved delineation of anatomical structures ( p < 0.01) compared to the conventional T2‐weighted HASTE sequence. DL sequences exhibited better SNR ( p < 0.001), whereas CNR values did not show a difference between the two acquisition types. Radiomics feature analysis unveiled significant differences in contrast and gray‐level characteristics ( p ≤ 0.001). DL HASTE demonstrated a significant time reduction of 62.5% together with significant energy cost savings of 0.34 kW per scan compared to the conventional sequence acquisition. The DL HASTE sequence enhanced image quality and diagnostic confidence while minimizing artifacts, time, and energy costs, enabling a more accurate detection of pathologies than the conventional T2‐weighted product solution with potential clinical impact.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Goethe University Hospital Frankfurt, Frankfurt am Main, Germany.
- EMEA Scientific Partnerships, Siemens Healthineers AG, Forchheim, Germany.
- MR Application Predevelopment, Siemens Healthineers AG, Forchheim, Germany.
- Department of Cardiology, Goethe University Hospital Frankfurt, Frankfurt am Main, Germany.
- Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy.
- University Hospital, Department of Cardiology, Angiology, and Pulmonology, University of Heidelberg, Heidelberg, Germany.
ORCID-Profile: Jennifer Gotta, Paul Konrad, Philipp Reschke, Sebastian M Haberkorn, Tommaso D'Angelo
Förderung
- Wilhelm Vaillant Stiftung
Zitieren
APA
Gotta, J., Bachir, A. A., Gruenewald, L. D., Strecker, R., Nickel, D., Martin, S. S., Booz, C., Mahmoudi, S., Al-Saleh, S., Dahm, D., Konrad, P., Bernatz, S., Reschke, P., Höhne, E., Hammerstingl, R. M., Eichler, K., Gruber-Rouh, T., Haberkorn, S. M., D'Angelo, T., …, & Koch, V. (2026). Deep Learning HASTE for Upper Abdominal MRI: Improved Image Quality, Speed, and Energy Efficiency in a Prospective Study. NMR in Biomedicine. https://doi.org/10.1002/nbm.70183
Vancouver
Gotta J, Bachir AA, Gruenewald LD, Strecker R, Nickel D, Martin SS, et al. Deep Learning HASTE for Upper Abdominal MRI: Improved Image Quality, Speed, and Energy Efficiency in a Prospective Study. NMR in Biomedicine. 2026. doi:10.1002/nbm.70183
BibTeX
@article{Gotta2026,
author = {Gotta, Jennifer and Bachir, Ahmed Ait and Gruenewald, Leon D and Strecker, Ralph and Nickel, Dominik and Martin, Simon S and Booz, Christian and Mahmoudi, Scherwin and Al-Saleh, Saber and Dahm, Daniel and Konrad, Paul and Bernatz, Simon and Reschke, Philipp and Höhne, Elena and Hammerstingl, Renate M and Eichler, Katrin and Gruber-Rouh, Tatjana and Haberkorn, Sebastian M and D'Angelo, Tommaso and Weber, Christophe and Zeuzem, Stefan and Wiegering, Armin and Sinkus, Ralph and Vogl, Thomas J and Koch, Vitali},
title = {Deep Learning HASTE for Upper Abdominal MRI: Improved Image Quality, Speed, and Energy Efficiency in a Prospective Study},
journal = {NMR in Biomedicine},
year = {2026},
doi = {10.1002/nbm.70183}
}
EUVIMED