Literature DB >> 35713359

Deep-learning synthesized pseudo-CT for MR high-resolution pediatric cranial bone imaging (MR-HiPCB).

Parna Eshraghi Boroojeni1, Yasheng Chen2, Paul K Commean3, Cihat Eldeniz3, Gary B Skolnick4, Corinne Merrill4, Kamlesh B Patel4, Hongyu An1,2,3.   

Abstract

PURPOSE: CT is routinely used to detect cranial abnormalities in pediatric patients with head trauma or craniosynostosis. This study aimed to develop a deep learning method to synthesize pseudo-CT (pCT) images for MR high-resolution pediatric cranial bone imaging to eliminating ionizing radiation from CT.
METHODS: 3D golden-angle stack-of-stars MRI were obtained from 44 pediatric participants. Two patch-based residual UNets were trained using paired MR and CT patches randomly selected from the whole head (NetWH) or in the vicinity of bone, fractures/sutures, or air (NetBA) to synthesize pCT. A third residual UNet was trained to generate a binary brain mask using only MRI. The pCT images from NetWH (pCTNetWH ) in the brain area and NetBA (pCTNetBA ) in the nonbrain area were combined to generate pCTCom . A manual processing method using inverted MR images was also employed for comparison.
RESULTS: pCTCom (68.01 ± 14.83 HU) had significantly smaller mean absolute errors (MAEs) than pCTNetWH (82.58 ± 16.98 HU, P < 0.0001) and pCTNetBA (91.32 ± 17.2 HU, P < 0.0001) in the whole head. Within cranial bone, the MAE of pCTCom (227.92 ± 46.88 HU) was significantly lower than pCTNetWH (287.85 ± 59.46 HU, P < 0.0001) but similar to pCTNetBA (230.20 ± 46.17 HU). Dice similarity coefficient of the segmented bone was significantly higher in pCTCom (0.90 ± 0.02) than in pCTNetWH (0.86 ± 0.04, P < 0.0001), pCTNetBA (0.88 ± 0.03, P < 0.0001), and inverted MR (0.71 ± 0.09, P < 0.0001). Dice similarity coefficient from pCTCom demonstrated significantly reduced age dependence than inverted MRI. Furthermore, pCTCom provided excellent suture and fracture visibility comparable to CT.
CONCLUSION: MR high-resolution pediatric cranial bone imaging may facilitate the clinical translation of a radiation-free MR cranial bone imaging method for pediatric patients.
© 2022 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  MRI; cranial bone imaging; craniosynostosis; deep learning; head trauma; pseudo-CT

Mesh:

Year:  2022        PMID: 35713359      PMCID: PMC9420780          DOI: 10.1002/mrm.29356

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   3.737


  50 in total

1.  Motion correction with PROPELLER MRI: application to head motion and free-breathing cardiac imaging.

Authors:  J G Pipe
Journal:  Magn Reson Med       Date:  1999-11       Impact factor: 4.668

2.  Self-gated MRI motion modeling for respiratory motion compensation in integrated PET/MRI.

Authors:  Robert Grimm; Sebastian Fürst; Michael Souvatzoglou; Christoph Forman; Jana Hutter; Isabel Dregely; Sibylle I Ziegler; Berthold Kiefer; Joachim Hornegger; Kai Tobias Block; Stephan G Nekolla
Journal:  Med Image Anal       Date:  2014-09-30       Impact factor: 8.545

3.  Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI.

Authors:  Hossein Arabi; Guodong Zeng; Guoyan Zheng; Habib Zaidi
Journal:  Eur J Nucl Med Mol Imaging       Date:  2019-07-01       Impact factor: 9.236

4.  Use of medical imaging procedures with ionizing radiation in children: a population-based study.

Authors:  Adam L Dorfman; Reza Fazel; Andrew J Einstein; Kimberly E Applegate; Harlan M Krumholz; Yongfei Wang; Emmanuel Christodoulou; Jersey Chen; Ramon Sanchez; Brahmajee K Nallamothu
Journal:  Arch Pediatr Adolesc Med       Date:  2011-01-03

5.  Three-Dimensional Reconstruction of the Craniofacial Skeleton With Gradient Echo Magnetic Resonance Imaging ("Black Bone"): What Is Currently Possible?

Authors:  Karen A Eley; Stephen R Watt-Smith; Stephen J Golding
Journal:  J Craniofac Surg       Date:  2017-03       Impact factor: 1.046

6.  PET/MR attenuation correction in brain imaging using a continuous bone signal derived from UTE.

Authors:  Claes Ladefoged; Didier Benoit; Ian Law; Soren Holm; Liselotte Hojgaard; Adam Espe Hansen; Flemming Littrup Andersen
Journal:  EJNMMI Phys       Date:  2015-12

7.  Magnetic resonance-based attenuation correction for PET/MR hybrid imaging using continuous valued attenuation maps.

Authors:  Bharath K Navalpakkam; Harald Braun; Torsten Kuwert; Harald H Quick
Journal:  Invest Radiol       Date:  2013-05       Impact factor: 6.016

8.  AI-driven attenuation correction for brain PET/MRI: Clinical evaluation of a dementia cohort and importance of the training group size.

Authors:  Claes Nøhr Ladefoged; Adam Espe Hansen; Otto Mølby Henriksen; Frederik Jager Bruun; Live Eikenes; Silje Kjærnes Øen; Anna Karlberg; Liselotte Højgaard; Ian Law; Flemming Littrup Andersen
Journal:  Neuroimage       Date:  2020-08-01       Impact factor: 6.556

9.  Technical Note: Deep learning based MRAC using rapid ultrashort echo time imaging.

Authors:  Hyungseok Jang; Fang Liu; Gengyan Zhao; Tyler Bradshaw; Alan B McMillan
Journal:  Med Phys       Date:  2018-05-15       Impact factor: 4.071

10.  3D pediatric cranial bone imaging using high-resolution MRI for visualizing cranial sutures: a pilot study.

Authors:  Kamlesh B Patel; Cihat Eldeniz; Gary B Skolnick; Udayabhanu Jammalamadaka; Paul K Commean; Manu S Goyal; Matthew D Smyth; Hongyu An
Journal:  J Neurosurg Pediatr       Date:  2020-06-12       Impact factor: 2.375

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.