Deep learning-based super-resolution gradient echo imaging of the pancreas: Improvement of image quality and reduction of acquisition time - 01/02/23
Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
Articolo gratuito.
Si connetta per beneficiarne
Highlights |
• | Deep learning-based super-resolution gradient echo imaging results in improved image quality and reduction of acquisition time for MRI of the pancreas. |
• | Deep learning-based super-resolution gradient echo imaging results in less image artifacts via simulated shortening of the acquisition time. |
• | Deep learning-based super-resolution gradient echo imaging can be easily implemented in post-processing workflow without protocol changes. |
Abstract |
Purpose |
The purpose of this study was to evaluate the impact of a deep learning-based super-resolution technique on T1-weighted gradient-echo acquisitions (volumetric interpolated breath-hold examination; VIBE) on the assessment of pancreatic MRI at 1.5 T compared to standard VIBE imaging (VIBESTD).
Materials and methods |
This retrospective single-center study was conducted between April 2021 and October 2021. Fifty patients with a total of 50 detectable pancreatic lesion entities were included in this study. There were 27 men and 23 women, with a mean age of 69 ± 13 (standard deviation [SD]) years (age range: 33–89 years). VIBESTD (precontrast, dynamic, postcontrast) was retrospectively processed with a deep learning-based super-resolution algorithm including a more aggressive partial Fourier setting leading to a simulated acquisition time reduction (VIBESR). Image analysis was performed by two radiologists regarding lesion detectability, noise levels, sharpness and contrast of pancreatic edges, as well as regarding diagnostic confidence using a 5-point Likert-scale with 5 being the best.
Results |
VIBESR was rated better than VIBESTD by both readers regarding lesion detectability (5 [IQR: 5, 5] vs. 5 [IQR: 4, 5], for reader 1; 5 [IQR: 5, 5] vs. 4 [IQR: 4, 5]) for reader 2; both P <0.001), noise levels (5 [IQR: 5, 5] vs. 5 [IQR: 4, 5] for reader 1; 5 [IQR: 5, 5] vs. 4 [IQR: 4, 5] for reader 2; both P <0.001), sharpness and contrast of pancreatic edges (5 [IQR: 5, 5] vs. 5 [IQR: 4, 5] for reader 1; 5 [IQR: 5, 5] vs. 4 [IQR: 4, 5] for reader 2; both P <0.001), as well as regarding diagnostic confidence (5 [IQR: 5, 5] vs. 5 [IQR: 4, 5] for reader 1; 5 [IQR: 5, 5] vs. 4 [IQR: 4, 5] for reader 2; both P <0.001). There were no significant differences between lesion sizes as measured by the two readers on VIBESR and VIBESTD images (P > 0.05). The mean acquisition time for VIBESTD (15 ± 1 [SD] s; range: 11–16 s) was longer than that for VIBESR (13 ± 1 [SD] s; range: 11–14 s) (P < 0.001).
Conclusion |
Our results indicate that the newly developed deep learning-based super-resolution algorithm adapted to partial Fourier acquisitions has a positive influence not only on shortening the examination time but also on improvement of image quality in pancreatic MRI.
Il testo completo di questo articolo è disponibile in PDF.Keywords : Deep learning, Magnetic resonance imaging, Pancreas, Gradient echo sequence
Abbreviations : 3D, DCE, DWI, GRE, HASTE, IQR, MRI, SNR, PI, PROPELLER, TA, VIBE, VIBESTD, VIBESR
Mappa
Vol 104 - N° 2
P. 53-59 - febbraio 2023 Ritorno al numero
Articolo precedente
- Spectral photon counting CT: Not just a pimped-up new version of dual-energy CT
- Sara Boccalini, Salim Si-Mohamed
- Transcatheter arterial embolization for cancer-related non-variceal upper gastrointestinal bleeding: A multicenter retrospective study of 107 patients
- Tao Gong, Jiaywei Tsauo, Mingchao Ding, Long Jin, Feng Duan, Youtao Yu, Xiao Li
Benvenuto su EM|consulte, il riferimento dei professionisti della salute.