Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 Tesla

Abstract Objective This prospective study aimed to assess the feasibility of a half-Fourier single-shot turbo spin echo sequence (HASTE) with deep learning (DL) reconstruction for ultrafast imaging of the bladder with reduced susceptibility to motion artifacts. Methods 50 patients underwent pelvic T...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Yan, Qinxuan Tan, David Kohnert, Marcel Dominik Nickel, Elisabeth Weiland, Felix Kubicka, Paul Jahnke, Dominik Geisel, Moritz Wagner, Thula Walter-Rittel
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01810-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738550693593088
author Li Yan
Qinxuan Tan
David Kohnert
Marcel Dominik Nickel
Elisabeth Weiland
Felix Kubicka
Paul Jahnke
Dominik Geisel
Moritz Wagner
Thula Walter-Rittel
author_facet Li Yan
Qinxuan Tan
David Kohnert
Marcel Dominik Nickel
Elisabeth Weiland
Felix Kubicka
Paul Jahnke
Dominik Geisel
Moritz Wagner
Thula Walter-Rittel
author_sort Li Yan
collection DOAJ
description Abstract Objective This prospective study aimed to assess the feasibility of a half-Fourier single-shot turbo spin echo sequence (HASTE) with deep learning (DL) reconstruction for ultrafast imaging of the bladder with reduced susceptibility to motion artifacts. Methods 50 patients underwent pelvic T2w imaging at 3 Tesla using the following MR sequences in sagittal orientation without antiperistaltic premedication: T2-TSE (time of acquisition [TA]: 2.03–4.00 min), standard HASTE (TA: 0.65–1.10 min), and DL-HASTE (TA: 0.25–0.47 min), with a slice thickness of 3 mm and a varying number of slices (25–45). Three radiologists evaluated the image quality of the three sequences quantitatively and qualitatively. Results Overall image quality of DL-HASTE (average score: 5) was superior to HASTE and T2-TSE (p < .001). DL-HASTE provided the clearest bladder wall delineation, especially in the apical part of the bladder (p < .001). SNR (36.3 ± 6.3) and CNR (50.3 ± 19.7) were the highest on DL-HASTE, followed by T2-TSE (33.1 ± 6.3 and 44.3 ± 21.0, respectively; p < .05) and HASTE (21.7 ± 5.4 and 35.8 ± 17.5, respectively; p < .01). A limitation of DL-HASTE and HASTE was the susceptibility to urine flow artifact within the bladder, which was absent or only minimal on T2-TSE. Diagnostic confidence in assessment of the bladder was highest with the combination of DL-HASTE and T2-TSE (p < .05). Conclusion DL-HASTE allows for ultrafast imaging of the bladder with high image quality and is a promising addition to T2-TSE.
format Article
id doaj-art-204fd74a236c48faadae1d0fc699b81b
institution DOAJ
issn 1471-2342
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-204fd74a236c48faadae1d0fc699b81b2025-08-20T03:06:31ZengBMCBMC Medical Imaging1471-23422025-07-0125111010.1186/s12880-025-01810-1Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 TeslaLi Yan0Qinxuan Tan1David Kohnert2Marcel Dominik Nickel3Elisabeth Weiland4Felix Kubicka5Paul Jahnke6Dominik Geisel7Moritz Wagner8Thula Walter-Rittel9Department of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthDepartment of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthDepartment of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthMR Application Predevelopment, Siemens Healthcare GmbHMR Application Predevelopment, Siemens Healthcare GmbHDepartment of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthDepartment of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthDepartment of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthDepartment of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthDepartment of Radiology, Charité - Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin Institute of HealthAbstract Objective This prospective study aimed to assess the feasibility of a half-Fourier single-shot turbo spin echo sequence (HASTE) with deep learning (DL) reconstruction for ultrafast imaging of the bladder with reduced susceptibility to motion artifacts. Methods 50 patients underwent pelvic T2w imaging at 3 Tesla using the following MR sequences in sagittal orientation without antiperistaltic premedication: T2-TSE (time of acquisition [TA]: 2.03–4.00 min), standard HASTE (TA: 0.65–1.10 min), and DL-HASTE (TA: 0.25–0.47 min), with a slice thickness of 3 mm and a varying number of slices (25–45). Three radiologists evaluated the image quality of the three sequences quantitatively and qualitatively. Results Overall image quality of DL-HASTE (average score: 5) was superior to HASTE and T2-TSE (p < .001). DL-HASTE provided the clearest bladder wall delineation, especially in the apical part of the bladder (p < .001). SNR (36.3 ± 6.3) and CNR (50.3 ± 19.7) were the highest on DL-HASTE, followed by T2-TSE (33.1 ± 6.3 and 44.3 ± 21.0, respectively; p < .05) and HASTE (21.7 ± 5.4 and 35.8 ± 17.5, respectively; p < .01). A limitation of DL-HASTE and HASTE was the susceptibility to urine flow artifact within the bladder, which was absent or only minimal on T2-TSE. Diagnostic confidence in assessment of the bladder was highest with the combination of DL-HASTE and T2-TSE (p < .05). Conclusion DL-HASTE allows for ultrafast imaging of the bladder with high image quality and is a promising addition to T2-TSE.https://doi.org/10.1186/s12880-025-01810-1Magnetic resonance imagingDeep learningHASTETurbo spin echo sequenceBladder imaging
spellingShingle Li Yan
Qinxuan Tan
David Kohnert
Marcel Dominik Nickel
Elisabeth Weiland
Felix Kubicka
Paul Jahnke
Dominik Geisel
Moritz Wagner
Thula Walter-Rittel
Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 Tesla
BMC Medical Imaging
Magnetic resonance imaging
Deep learning
HASTE
Turbo spin echo sequence
Bladder imaging
title Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 Tesla
title_full Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 Tesla
title_fullStr Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 Tesla
title_full_unstemmed Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 Tesla
title_short Ultrafast T2-weighted MR imaging of the urinary bladder using deep learning-accelerated HASTE at 3 Tesla
title_sort ultrafast t2 weighted mr imaging of the urinary bladder using deep learning accelerated haste at 3 tesla
topic Magnetic resonance imaging
Deep learning
HASTE
Turbo spin echo sequence
Bladder imaging
url https://doi.org/10.1186/s12880-025-01810-1
work_keys_str_mv AT liyan ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT qinxuantan ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT davidkohnert ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT marceldominiknickel ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT elisabethweiland ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT felixkubicka ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT pauljahnke ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT dominikgeisel ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT moritzwagner ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla
AT thulawalterrittel ultrafastt2weightedmrimagingoftheurinarybladderusingdeeplearningacceleratedhasteat3tesla