Acquisition time reduction of diffusion-weighted liver imaging using deep learning image reconstruction - 30/03/23
, Judith Herrmann a, Haidara Almansour a, Thomas Benkert b, Elisabeth Weiland b, Thomas Hölldobler a, Konstantin Nikolaou a, c, Sebastian Gassenmaier a
Bienvenido a EM-consulte, la referencia de los profesionales de la salud.
Artículo gratuito.
Conéctese para beneficiarse!
Highlights |
• | Deep learning image reconstruction of diffusion-weighted liver imaging including acquisition time reduction of more than 40% is feasible without loss of image quality. |
• | Deep learning image reconstruction of diffusion-weighed liver imaging provides significant reduction of the noise (P < 0.001). |
• | Deep learning image reconstruction of diffusion-weighted liver imaging provides significantly greater signal intensities on ADC map for the liver, spleen, and erector spinae muscles. |
Abstract |
Purpose |
The purpose of this study was to investigate the impact of deep learning accelerated diffusion-weighted imaging (DWIDL) in 1.5-T liver MRI on image quality, sharpness, and diagnostic confidence.
Materials and methods |
One-hundred patients who underwent liver MRI at 1.5-T including DWI with two different b-values (50 and 800 s/mm²) between February and April 2022 were retrospectively included. There were 54 men and 46 women, with a mean age of 59 ± 14 (SD) years (range: 21–88 years). The single average raw data were retrospectively processed using a deep learning (DL) image reconstruction algorithm leading to a simulated acquisition time of 1 min 28 s for DWIDL as compared to 2 min 31 s for standard DWI (DWIStd) via reduction of signal averages. All DWI datasets were reviewed by four radiologists using a Likert scale ranging from 1–4 using the following criteria: noise level, extent of artifacts, sharpness, overall image quality, and diagnostic confidence. Furthermore, quantitative assessment of noise and signal-to-noise ratio (SNR) was performed via regions of interest.
Results |
No significant differences were found regarding artifacts and overall image quality (P > 0.05). Noise measurements for the spleen, liver, and erector spinae muscles revealed significantly lower noise for DWIDL versus DWIStd (P < 0.001). SNR measurements in the above-mentioned tissues also showed significantly superior results for DWIDL versus DWIStd for b = 50 s/mm² and ADC maps (all P < 0.001). For b = 800 s/mm², significantly superior results were found for the spleen, right hemiliver, and erector spinae muscles.
Conclusions |
DL image reconstruction of liver DWI at 1.5-T is feasible including significant reduction of acquisition time without compromised image quality.
El texto completo de este artículo está disponible en PDF.Keywords : Deep learning, Diffusion-weighted imaging, Image reconstruction, Liver, Magnetic resonance imaging, Signal-to-noise ratio
Abbreviations : ADC, DL, DLR, DWI, DWIStd, DWIDL, GRE, MRI, PI, ROI, SD, SI, SMS, SNR, TA, TSE
Esquema
Vol 104 - N° 4
P. 178-184 - avril 2023 Regresar al número
Artículo precedente
- Spectral CT imaging: Technical principles of dual-energy CT and multi-energy photon-counting CT
- Joël Greffier, Nicolas Villani, Didier Defez, Djamel Dabli, Salim Si-Mohamed
- Lung shunt fraction calculations before Y-90 transarterial radioembolization: Comparison of accuracy and clinical significance of planar scintigraphy and SPECT/CT
- Shamar Young, Siobhan Flanagan, Donna D'Souza, Soorya Todatry, Ranjan Ragulojan, Tina Sanghvi, Jafar Golzarian
Bienvenido a EM-consulte, la referencia de los profesionales de la salud.