What question did this study set out to answer?

This research aims to enhance the speed and quality of MRI reconstructions through a deep learning approach.

July 24, 2018Radiology

Variable-Density Single-Shot Fast Spin-Echo MRI with Deep Learning Reconstruction by Using Variational Networks

View Full Paper

Ask AI

Bookmark

This research aims to enhance the speed and quality of MRI reconstructions through a deep learning approach.
Used a 3.0-T MRI imager with variable-density fast spin-echo sequence at 3.25x acceleration in 157 patients.
Trained a variational network (VN) on 130 patients and evaluated on 27 patients for image quality.
Image quality assessed by three blinded radiologists using a scoring system from 1 to 5.
VN achieved a higher perceived signal-to-noise ratio (P = .01) and sharpness (P < .001).
Overall image quality was better in VN compared to conventional method (P = .02).
Average reconstruction time for VN was 0.19 seconds, much faster than PICS at 5.60 seconds.

No takes yet. Share an insight, caveat, or question.

Randomized trial evaluates image quality improvements in abdominal MRI using deep learning techniques.

Chen et al. (2018) studied this question.

View Full Paper

Ask AI

Bookmark