Feasibility of deep learning-accelerated ultrafast T1-weighted VIBE Dixon imaging of the pelvis for screening of metastases in prostate MRI

OBJECTIVE: This study aims to assess the image quality and perceived diagnostic confidence of research deep learning (DL)-accelerated T1-weighted "volumetric interpolated breath‑hold examination" (VIBE) Dixon sequences compared to conventional T1-weighted VIBE Dixon sequences for the screening of pelvic metastases in prostate magnetic resonance imaging (MRI). MATERIALS AND METHODS: Consecutive patients receiving prostate MRI between February and April 2024 were prospectively included. In addition to the conventional T1-weighted VIBE Dixon sequences (T1STD), two research DL-accelerated sequences (T1DL, T1DL FAST) with different acceleration were acquired. Three blinded radiologists assessed image quality and perceived diagnostic confidence on a Likert scale (from 1 = non-diagnostic to 5 = excellent). Signal homogeneity was measured for quantitative assessment. RESULTS: Fifty-four patients were included, aged 68 ± 6.6 years (mean ± standard deviation). The DL-accelerated sequences had markedly shorter acquisition time (15 s and 45 s versus 143 s). Overall image quality was comparable or superior, with especially improved sharpness in contrast-enhanced imaging (median [interquartile range]: T1STD = 4 [3‒4] versus T1DL = 5 [5‒5] versus T1DL FAST = 4 [4‒5]; p < 0.001). Although a slight increase in artifacts and signal inhomogeneity was noted, the diagnostic confidence was equally excellent with a median score of 5 [5‒5] and with p values ranging from 0.276 to < 0.001. CONCLUSION: DL-accelerated T1-weighted VIBE Dixon imaging in prostate MRI is feasible and demonstrates good image quality and equally high perceived diagnostic confidence for pelvic metastases with a tremendously shorter acquisition time. RELEVANCE STATEMENT: The availability of prostate MRI is significantly influenced by acquisition time. To meet the increasing demand for prostate MRI, DL-accelerated sequences provide faster and more efficient image reconstruction. KEY POINTS: DL-accelerated T1-weighted VIBE Dixon sequences in prostate MRI address the growing demand for rapid, high-quality imaging in prostate cancer assessment. DL-acceleration reduces sequence acquisition time from 143 s to 15 s without loss of image quality and perceived diagnostic confidence. DL-accelerated T1-weighted VIBE Dixon sequences enable more efficient, time-saving prostate MRI to increase availability and patient throughput.

Authors

Institutions

Publication Details

Journal
European Radiology Experimental
Published
2026-06-25
DOI
https://doi.org/10.1186/s41747-026-00758-3
Primary Topic
Prostate Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Feasibility of deep learning-accelerated ultrafast T1-weighted VIBE Dixon imaging of the pelvis for screening of metastases in prostate MRI

Fabian Bamberg, Caroline Wilpert, Benedict Oerther, Ralph Strecker et al.
European Radiology Experimental
Prostate Cancer Diagnosis and Treatment
article

Feasibility of deep learning-accelerated ultrafast T1-weighted VIBE Dixon imaging of the pelvis for screening of metastases in prostate MRI

Fabian Bamberg, Caroline Wilpert, Benedict Oerther, Ralph Strecker, Andrea Nedelcu, Hannes Engel, Dominik Marcel Nickel, Jakob Weiß, Maximilian Frederic Russe
article en

Abstract

OBJECTIVE: This study aims to assess the image quality and perceived diagnostic confidence of research deep learning (DL)-accelerated T1-weighted "volumetric interpolated breath‑hold examination" (VIBE) Dixon sequences compared to conventional T1-weighted VIBE Dixon sequences for the screening of pelvic metastases in prostate magnetic resonance imaging (MRI). MATERIALS AND METHODS: Consecutive patients receiving prostate MRI between February and April 2024 were prospectively included. In addition to the conventional T1-weighted VIBE Dixon sequences (T1STD), two research DL-accelerated sequences (T1DL, T1DL FAST) with different acceleration were acquired. Three blinded radiologists assessed image quality and perceived diagnostic confidence on a Likert scale (from 1 = non-diagnostic to 5 = excellent). Signal homogeneity was measured for quantitative assessment. RESULTS: Fifty-four patients were included, aged 68 ± 6.6 years (mean ± standard deviation). The DL-accelerated sequences had markedly shorter acquisition time (15 s and 45 s versus 143 s). Overall image quality was comparable or superior, with especially improved sharpness in contrast-enhanced imaging (median [interquartile range]: T1STD = 4 [3‒4] versus T1DL = 5 [5‒5] versus T1DL FAST = 4 [4‒5]; p < 0.001). Although a slight increase in artifacts and signal inhomogeneity was noted, the diagnostic confidence was equally excellent with a median score of 5 [5‒5] and with p values ranging from 0.276 to < 0.001. CONCLUSION: DL-accelerated T1-weighted VIBE Dixon imaging in prostate MRI is feasible and demonstrates good image quality and equally high perceived diagnostic confidence for pelvic metastases with a tremendously shorter acquisition time. RELEVANCE STATEMENT: The availability of prostate MRI is significantly influenced by acquisition time. To meet the increasing demand for prostate MRI, DL-accelerated sequences provide faster and more efficient image reconstruction. KEY POINTS: DL-accelerated T1-weighted VIBE Dixon sequences in prostate MRI address the growing demand for rapid, high-quality imaging in prostate cancer assessment. DL-acceleration reduces sequence acquisition time from 143 s to 15 s without loss of image quality and perceived diagnostic confidence. DL-accelerated T1-weighted VIBE Dixon sequences enable more efficient, time-saving prostate MRI to increase availability and patient throughput.

European Radiology ExperimentalVol. 10(1)
Siemens (Germany) (DE), University of Freiburg (DE), University Medical Center Freiburg (DE), Siemens Healthineers (Germany) (DE)
Openalex Percentile: Top 8%
Prostate Cancer Diagnosis and Treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.