Improved neonatal brain MRI segmentation by interpolation of motion corrupted slices
Verschuur, Anouk S; Boswinkel, Vivian; Tax, Chantal M W; van Osch, Jochen A C; Nijholt, Ingrid M; Slump, Cornelis H; de Vries, Linda S; van Wezel-Meijler, Gerda; Leemans, Alexander; Boomsma, Martijn F
(2022) Journal of Neuroimaging, volume 32, issue 3, pp. 480 - 492
(Article)
Abstract
BACKGROUND AND PURPOSE: To apply and evaluate an intensity-based interpolation technique, enabling segmentation of motion-affected neonatal brain MRI. METHODS: Moderate-late preterm infants were enrolled in a prospective cohort study (Brain Imaging in Moderate-late Preterm infants "BIMP-study") between August 2017 and November 2019. T2-weighted MRI was performed around term equivalent age
... read more
on a 3T MRI. Scans without motion (n = 27 [24%], control group) and with moderate-severe motion (n = 33 [29%]) were included. Motion-affected slices were re-estimated using intensity-based shape-preserving cubic spline interpolation, and automatically segmented in eight structures. Quality of interpolation and segmentation was visually assessed for errors after interpolation. Reliability was tested using interpolated control group scans (18/54 axial slices). Structural similarity index (SSIM) was used to compare T2-weighted scans, and Sørensen-Dice was used to compare segmentation before and after interpolation. Finally, volumes of brain structures of the control group were used assessing sensitivity (absolute mean fraction difference) and bias (confidence interval of mean difference). RESULTS: Visually, segmentation of 25 scans (22%) with motion artifacts improved with interpolation, while segmentation of eight scans (7%) with adjacent motion-affected slices did not improve. Average SSIM was .895 and Sørensen-Dice coefficients ranged between .87 and .97. Absolute mean fraction difference was ≤0.17 for less than or equal to five interpolated slices. Confidence intervals revealed a small bias for cortical gray matter (0.14-3.07 cm3 ), cerebrospinal fluid (0.39-1.65 cm3 ), deep gray matter (0.74-1.01 cm3 ), and brainstem volumes (0.07-0.28 cm3 ) and a negative bias in white matter volumes (-4.47 to -1.65 cm3 ). CONCLUSION: According to qualitative and quantitative assessment, intensity-based interpolation reduced the percentage of discarded scans from 29% to 7%.
show less
Download/Full Text
Keywords: interpolation, motion artifacts, MRI, neonatal, segmentation, Clinical Neurology, Radiology Nuclear Medicine and imaging, Journal Article
ISSN: 1051-2284
Publisher: Wiley-Blackwell
Note: Funding Information: INFORMATIONThis research was supported by the Isala Science and Innovation Fund (Isala Hospital, Zwolle, the Netherlands), the Dr. C. J. Vaillant Fund (Landelijke Vereniging van Crematoria, Almere, the Netherlands), and Nutricia Specialized Nutrition (Nutricia Nederland B.V., Zoetermeer, the Netherlands). The sponsors had no role in the design and conduct of the study, collection, management, analysis, and interpretation of the data, or in the preparation, review, approval of the manuscript, or decision to submit the manuscript for publication.We thank Dr. K. L. Vinken and Dr. H. J. Kuijf (University Medical Centre Utrecht) for their expert advice throughout this project. The authors would like to thank all infants and their parents for their participation. We are grateful to the physicians, (research-) nurses, and radiology technicians involved in the BIMP study for their contribution. The authors declare no conflict of interest Verschuur AS, Boswinkel V, van Osch JAC, et al. Cubic interpolation for automatic brain segmentation of MRI motion artifacts in moderate and late preterm infants (Abstract ID: 200144983). Radiological Society of North America 2020. Funding Information: This research was supported by the Isala Science and Innovation Fund (Isala Hospital, Zwolle, the Netherlands), the Dr. C. J. Vaillant Fund (Landelijke Vereniging van Crematoria, Almere, the Netherlands), and Nutricia Specialized Nutrition (Nutricia Nederland B.V., Zoetermeer, the Netherlands). The sponsors had no role in the design and conduct of the study, collection, management, analysis, and interpretation of the data, or in the preparation, review, approval of the manuscript, or decision to submit the manuscript for publication. FUNDING INFORMATION Publisher Copyright: © 2022 The Authors. Journal of Neuroimaging published by Wiley Periodicals LLC on behalf of American Society of Neuroimaging.
(Peer reviewed)
