Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Sep 18;25(1):369.
doi: 10.1186/s12880-025-01838-3.

Optimized deep learning-accelerated single-breath-hold abdominal HASTE with and without fat saturation improves and accelerates abdominal imaging at 3 Tesla

Qinxuan Tan  1 , Felix Kubicka  1 , Dominik Nickel  2 , Elisabeth Weiland  2 , Bernd Hamm  1 , Dominik Geisel  1 , Moritz Wagner  1 , Thula C Walter-Rittel  3
Affiliations

Optimized deep learning-accelerated single-breath-hold abdominal HASTE with and without fat saturation improves and accelerates abdominal imaging at 3 Tesla

Qinxuan Tan et al. BMC Med Imaging. .

Abstract

Background: Deep learning-accelerated single-shot turbo-spin-echo techniques (DL-HASTE) enable single-breath-hold T2-weighted abdominal imaging. However, studies evaluating the image quality of DL-HASTE with and without fat saturation (FS) remain limited. This study aimed to prospectively evaluate the technical feasibility and image quality of abdominal DL-HASTE with and without FS at 3 Tesla.

Materials and methods: DL-HASTE of the upper abdomen was acquired with variable sequence parameters regarding FS, flip angle (FA) and field of view (FOV) in 10 healthy volunteers and 50 patients. DL-HASTE sequences were compared to clinical sequences (HASTE, HASTE-FS and T2-TSE-FS BLADE). Two radiologists independently assessed the sequences regarding scores of overall image quality, delineation of abdominal organs, artifacts and fat saturation using a Likert scale (range: 1-5).

Results: Breath-hold time of DL-HASTE and DL-HASTE-FS was 21 ± 2 s with fixed FA and 20 ± 2 s with variable FA (p < 0.001), with no overall image quality difference (p > 0.05). DL-HASTE required a 10% larger FOV than DL-HASTE-FS to avoid aliasing artifacts from subcutaneous fat. Both DL-HASTE and DL-HASTE-FS had significantly higher overall image quality scores than standard HASTE acquisitions (DL-HASTE vs. HASTE: 4.8 ± 0.40 vs. 4.1 ± 0.50; DL-HASTE-FS vs. HASTE-FS: 4.6 ± 0.50 vs. 3.6 ± 0.60; p < 0.001). Compared to the T2-TSE-FS BLADE, DL-HASTE-FS provided higher overall image quality (4.6 ± 0.50 vs. 4.3 ± 0.63, p = 0.011). DL-HASTE achieved significant higher image quality (p = 0.006) and higher sharpness score of organs compared to DL-HASTE-FS (p < 0.001).

Conclusion: Deep learning-accelerated HASTE with and without fat saturation were both feasible at 3 Tesla and showed improved image quality compared to conventional sequences.

Trial registration: Not applicable.

Keywords: Abdomen; Artificial intelligence; Deep learning; Magnetic resonance imaging.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: This study was approved by the local ethics committee (Ethik Kommission Universitätsmedizin Charité Berlin Hospital], approval number [EA1/344/21], and conducted in accordance with the Declaration of Helsinki. Written informed consent was obtained from all participants and patients. Consent for publication: Written and informed consent for publication of anonymised data was obtained from all participants and patients. Competing interests: Prof. Dr. Bernd Hamm has relationships with the following companies or institutions: Abbott, AbbVie, Ablative Solutions, Accovion, Achaogen Inc. Actelion Pharmaceutical. ADIR. Aesculap. Agios Pharmaceuticals, INC. AGO. AIF Arbeitsgemeinschaft industrieller Forschungsvereinigungen, AIO Arbeitsgemeinschaft Internistische Onkologie, Aktionsbündnis Patientensicherheit e.V. Alexion Pharmaceuticals. Amgen. AO Foundation. Arena Pharmaceuticals. ARMO Biosciences, Inc. Art photonics GmbH Berlin. ASAS, Ascelia Pharma AB, Ascendis, ASR Advanced sleep research, Astellas, BARD, Basiliea, Bayer Healthcare, Bayer Vital, Braun, BerGenBioASA, Berlin-Brandenburger Centrum für Regenerative Therapie (BCRT), Berliner Krebsgesellschaft, Biontech Mainz, BioNTech SE, Biotronik, Bioven, BMBF, Boehring Ingelheimer, Boston Biomedical Inc., Boston Scientific Medizintechnik GmbH, BRACCO Broup, Brahms GmbH, Brainsgate, Bristol-Myers Squibb, Calithera Biosciences UK, Cantargia AB, Medicon Village, Cascadian Therapeutics, Inc., Celgene, CELLACT Pharma, Celldex Therapeutics, Cellestia Biontech AG CH, CeloNova BioSciences, Charité research organization GmbH, Chiltern, CLOVIS ONCOLOGY, Inc., Covance, CRO Chrarité, CUBIST, CureVac AG, Tübingen, Curis, Daiichi Sankyo, Dartmouth College, Hanover, NH, USA, DC Devices, Inc. USA, Delcath Systems, Dermira Inc., Deutsche Krebshilfe, Deutsche Rheuma Liga, DZ-Deutsches Diabetes Forschungsgesellschaft e.V., Deutsches Zentrum für Luft- und Raumfahrt e.V., DFG, Dr. Falk Pharma GmbH, DSM Nutritional Products AG, Dt. Stiftung für Herzforschung, Dynavax, Eisai Ltd., European Knowledge Centre, Mosquito Way, Hatfield, Eli Lilly and Conpany Ltd., EORTC, Episurf Medical, Epizyme, Inc., Essex Pharma, EU Programmes, Euroscreen S.A., F20 Biotech GmbH, Ferring Pharmaceuticals A/S, Fibrex Medical Inc., Focussed Ultrasound Surgery Foundation, Fraunhofer Gesellschaft, Galena Biopharma, Galmed Research and Development Ltd., Ganymed, GBG Forschung BmbH, GE, Gentech, Inc., Genmab A/S, Genzyme Europe B.V., GETNE (Grupo Español de Tumores Neuroendocrinos, Gilead Sciences, Inc., Glaxo Smith Kline, Glycotope GmbH, Berlin, Goethe Uni Frankfurt, Guerbet. Guidant Europe NV, Halozyme, Hans-Blöckler-Stiftung, Hewlett Packard GmbH, Holaira, Inc., Horizon Therapeutics Ireland, ICON (CRO), Idera Pharmaceutics, Inc., Ignyta, Inc., Immunimedics, Inc., Immunocore, Incyte, INC Research, Innate Pharma, InSightec Ltd, Inspiremd, inVentiv Health Clinical UK Ltd., Inventivhealth, IOMEDICO IONIS IPSEN Pharma IQVIA ISA Therapeutics Isis Pharmaceuticals, Inc. ITM Solucin GmbH Jansen-Cilag GmbH Kantar Health GmbH (CRO) Kartos Therapeutics, Inc. Karyopharm Therapeutics, Inc. Kendle/MorphoSys AG Kite Pharma Kli Fo Berlin Mitte Kura Oncology, Inc. La Roche Land Berlin Lilly GmbH Lion Biontechnology Lombard Medical Loxo Oncology, Inc. LSK BioPartner, USA Lundbeck GmbH LUX Biosciences LYSARC MacroGenics MagForce MedImmune, Inc, Medpace Germany GmbH (CRO) MedPass (CRO) Medronic Medtraveö GmbH Merck Merrimack Pharmaceuticals, Inc. MeVis Medical Solutions AG Miltenyi Biomedicine GmbH, Bergisch Gladbach miRagen Boukider Mologen MorphoSysAG MSD Sharp Nektar Therapeutics NeoVacs SA Newlink Genetics Corporation Nexus Oncology NIH NOGGO Berlin, Novartis, Novocure, Nuvisan, Ockham oncology, Odonate Therapeutics San Diago. OHIRC Kanada, Orion Corporation Orion Pharma, OSE Immunitherapeutics, Parexel CRO Service, PentixalPharmGmbH, Perceptive. Pfizer GmbH, PharmaCept GmbH, Pharma Mar, Pharmaceutical Research Associates GmbH (PRA), Pharmacyclines, Inc., Philipps, Philogen s.p.a.Siena, Pliant Therapeutics San Francisco, PIQUR Therapeutics Ltd., Pluristem, PneumRX, Inc., Portola Pharmaceuticals, PPD (CRO), PRAint, Premier-research, Provectus Biopharmaceuticals, Inc., Psi-cro, Pulmonx International Sàrl Quintiles GmbH Radiobotics ApS Regeneron Pharmaceuticals, Inc. Replimune Respicardia Rhythm Pharmaceuticals, Inc., Boston USA Roche Salix Pharmaceuticals, Inc. Samsung Sanofi Sanofis-aventis S.A. Saving Patient´s Lives Medical B.V. Schumacher GmbH Seattle Genetics Servier (CRO) SGS Life Science Service (CRO) Shire Human Genetic Therapies Siemens Silena Therapeutics SIRTEX Medical Europe GmbH Spectranetics GmbH Spectrum Pharmaceuticals Stiftung Charité/ BIH St. Jude Medical Stiftung Wolfgang Schulze Syneos Health UK, Limited, Symphogen Taiho Oncology, Inc. Taiho Pharmaceutical Co. Target Pharma Solutions, Inc. TauRx Therapeutics Ltd. Terumo Medical Corporation Tesaro Tetec-ag TEVA Theorem Rheradex Theravance Threshold Pharmaceuticals, Inc. TNS Healthcare GmbH Toshiba UCB Pharma Uni Jena Uni München Uni Tübingen Vaccibody A.S. VDI/VDE, Vertex Pharmaceuticals Incorporated Virtualscopis LLC, Winicker-norimed, Wyeth Pharma, Xcovery Holding Company. Zukunftsfond Berlin (TSB)Dominik Geisel is a section editor for BMC medical imaging and reports speaker honoraria for Siemens Healthineers.Dominik Nickel, Elisabeth Weiland, Qinxuan Tan, Felix-Maximilian Kubicka, Moritz Wagner and Thula C. Walter-Rittel declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Figures

Fig. 1
Fig. 1
Effect of FOV size on image quality of DL-HASTE FS and DL-HASTE from one same volunteer (a1: HASTE-FS, a2-a5: DL-HASTE-FS; b1: standard HASTE, b2-b5 DL-HASTE). The comparison was performed using a variable FA scheme set at 130–90–110–130°. To avoid fold-over type artifacts (arrows), the FOV needed to be about 10% larger in DL-HASTE compared to DL-HASTE-FS
Fig. 2
Fig. 2
A 75-year-old woman with a pancreatic lesion. Comparing overall image quality of DL-HASTE (a) and DL-HASTE-FS (c) with standard multi-breath hold HASTE (b) and HASTE-FS (d) as well as navigator triggered T2-TSE-FS BLADE (e). Image quality was rated highest for DL-HASTE (a) and DL-HASTE-FS (c). In Fig. 2c and d, the dark band-like signal loss observed in the subcutaneous fat likely results from inhomogeneous fat suppression using the SPAIR technique, which can be affected by B₀ field non-uniformity in the upper abdominal region
Fig. 3
Fig. 3
Sharpness of organ margins with DL-HASTE (a, c, e, g) compared to HASTE (b, d, f, h). DL-HASTE received the highest scores for all upper abdominal organ margins. All images were acquired in the same patient
Fig. 4
Fig. 4
Comparison of organ margin delineation in T2-TSE-FS BLADE (a, d, g) with DL-HASTE-FS (b, e, h), and DL-HASTE (c, f, i) in three patients with cystic pancreatic lesions (arrows) in the head (a-c), body (d-f), and tail (g-i). Note the optimal visualization of pancreatic anatomy with DL-HASTE
See this image and copyright information in PMC

References

    1. Dujardin M, Vandenbroucke F, Boulet C, Op de Beeck B, de Mey J. Indications for body MRI part I. Upper abdomen and renal imaging. Eur J Radiol. 2008;65(2):214–21. 10.1016/j.ejrad.2007.11.015. - DOI - PubMed
    1. Donato H, França M, Candelária I, Caseiro-Alves F, Liver MRI. From basic protocol to advanced techniques. Eur J Radiol. 2017;93:30–9. 10.1016/j.ejrad.2017.05.028. - DOI - PubMed
    1. Krishna S, Schieda N, Flood TA, Shanbhogue AK, Ramanathan S, Siegelman E. Magnetic resonance imaging (MRI) of the renal sinus. Abdom Radiol (NY). 2018;43(11):3082–100. 10.1007/s00261-018-1593-1. - DOI - PubMed
    1. Merkle EM, Dale BM, Paulson EK. Abdominal MR imaging at 3T. Magn reson imaging clin N am. 2006;14(1):17–26. 10.1016/j.mric.2005.12.001 - PubMed
    1. Choi JY, Kim MJ, Chung YE, Kim JY, Jones AC, de Becker J, van Cauteren M. Abdominal applications of 3.0-T MR imaging: comparative review versus a 1.5-T system. Radiographics 2008 Jul-Aug;28(4): e30. 10.1148/rg.e30 - PubMed

Publication types

LinkOut - more resources