Premium
Data Quality Assessment for Super‐Resolution Fetal Brain MR Imaging: A Retrospective 1.5 T Study
Author(s) -
Rubert Nicholas,
Bardo Dianna M.E.,
Vaughn Jennifer,
Cornejo Patricia,
Goncalves Luis F.
Publication year - 2021
Publication title -
journal of magnetic resonance imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.563
H-Index - 160
eISSN - 1522-2586
pISSN - 1053-1807
DOI - 10.1002/jmri.27665
Subject(s) - correlation , voxel , image quality , nuclear medicine , magnetic resonance imaging , medicine , radiology , mathematics , artificial intelligence , computer science , image (mathematics) , geometry
Background Super‐resolution is a promising technique to create isotropic image volumes from stacks of two‐dimensional (2D) motion‐corrupted images in fetal magnetic resonance imaging (MRI). Purpose To determine an acquisition quality metric and correlate that metric with radiologist perception of three‐dimensional (3D) image quality. Study Type Retrospective. Subjects Eighty‐seven patients, mean gestational age 29 ± 6 weeks. Field Strength/Sequence 1.5 T/ 2D fast spin‐echo. Assessment Four radiologists (L.G., D.M.E.B., P.C., and J.V.; 31, 21, 7, and 7 years' experience, respectively) graded reconstructions on a 0 to 4 scale for overall appearance and visibility of specific anatomy. During reconstruction, slices were labeled as inliers based on correlation between a simulated vs. actual acquisition. The fraction of brain voxels in inlier slicers vs. total brain voxels was measured for each acquisition. Statistical Tests Paired sample t test, Pearson's correlation, intra‐class correlation. Results The average brain mask inlier fraction for all acquisitions was 0.8. There was a statistically significant correlation (0.71) between overall reconstruction appearance and number of acquisitions with inlier fraction above 0.73. There was low correlation (0.21, P = 0.05) between the number of acquisitions used in the reconstruction and overall score when no data quality measure was considered. Similar results were found for ratings of specific anatomy. Statistically significant differences in overall perception of image quality were found when using three vs. four, four vs. five, and three vs. five high‐quality acquisitions in the reconstruction. Five high‐quality acquisitions were sufficient to yield an average radiologist rating of 3.59 out of 4.0 for overall image quality. Data Conclusion Reconstruction quality can be reliably predicted using the brain mask inlier fraction. Real‐time super‐resolution protocols could exploit this to terminate acquisition when enough high‐quality acquisitions have been collected. To achieve consistent 3D image quality it may be necessary to acquire more than five scans to compensate for severely motion‐corrupted acquisitions. Level of Evidence 3 Technical Efficacy 1