EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Three contrasts in 3 min: Rapid, high‐resolution, and bone‐selective UTE MRI for craniofacial imaging with automated deep‐learning skull segmentation

Brian-Tinh Duc Vu iD, Nada Kamona, Yohan Kim, Jinggang J Ng, Brandon C Jones, Felix W Wehrli iD, Hee Kwon Song, Scott P Bartlett, Hyunyeol Lee iD, Chamith S Rajapakse

Magnetic Resonance in Medicine · 2025

DOI: 10.1002/mrm.30275 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2025. Verfasst von Brian-Tinh Duc Vu und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA. Hauptthemen laut MEDLINE: Deep Learning, Skull, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIAMS NIH HHS, NIH HHS, NIBIB NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Ultrashort echo time (UTE) MRI can be a radiation‐free alternative to CT for craniofacial imaging of pediatric patients. However, unlike CT, bone‐specific MR imaging is limited by long scan times, relatively low spatial resolution, and a time‐consuming bone segmentation workflow.

Methods

A rapid, high‐resolution UTE technique for brain and skull imaging in conjunction with an automatic segmentation pipeline was developed. A dual‐RF, dual‐echo UTE sequence was optimized for rapid scan time (3 min) and smaller voxel size (0.65 mm 3 ). A weighted least‐squares conjugate gradient method for computing the bone‐selective image improves bone specificity while retaining bone sensitivity. Additionally, a deep‐learning U‐Net model was trained to automatically segment the skull from the bone‐selective images. Ten healthy adult volunteers (six male, age 31.5 ± 10 years) and three pediatric patients (two male, ages 12 to 15 years) were scanned at 3 T. Clinical CT for the three patients were obtained for validation. Similarities in 3D skull reconstructions relative to clinical standard CT were evaluated based on the Dice similarity coefficient and Hausdorff distance. Craniometric measurements were used to assess geometric accuracy of the 3D skull renderings.

Results

The weighted least‐squares method produces images with enhanced bone specificity, suppression of soft tissue, and separation from air at the sinuses when validated against CT in pediatric patients. Dice similarity coefficient overlap was 0.86 ± 0.05, and the 95th percentile Hausdorff distance was 1.77 ± 0.49 mm between the full‐skull binary masks of the optimized UTE and CT in the testing dataset.

Conclusion

An optimized MRI acquisition, reconstruction, and segmentation workflow for craniofacial imaging was developed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSkullMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansMaleChildAdolescentFemaleAdultTomography, X-Ray ComputedBrainAlgorithmsYoung Adult

Stichwörter der Autor:innen

craniofacial imagingdual‐echo UTEimage reconstructionskull segmentationsolid‐state imagingultrashort echo time MRI

Autor:innen und Institutionen

  • Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
  • Department of Bioengineering, School of Engineering and Applied Sciences, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
  • Division of Plastic, Reconstructive and Oral Surgery, Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA.
  • School of Electronics Engineering, Kyungpook National University, Daegu, Republic of Korea.
  • Department of Orthopaedic Surgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA.

ORCID-Profile: Brian-Tinh Duc Vu, Felix W Wehrli, Hyunyeol Lee

Förderung

  • NIAMS NIH HHS
  • NIH HHS
  • NIBIB NIH HHS
  • NIDCR NIH HHS
  • National Science Foundation
  • National Science Foundation of Sri Lanka
  • National Institutes of Health

Zitieren

APA

Vu, B. D., Kamona, N., Kim, Y., Ng, J. J., Jones, B. C., Wehrli, F. W., Song, H. K., Bartlett, S. P., Lee, H., & Rajapakse, C. S. (2025). Three contrasts in 3 min: Rapid, high‐resolution, and bone‐selective UTE MRI for craniofacial imaging with automated deep‐learning skull segmentation. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30275

Vancouver

Vu BD, Kamona N, Kim Y, Ng JJ, Jones BC, Wehrli FW, et al. Three contrasts in 3 min: Rapid, high‐resolution, and bone‐selective UTE MRI for craniofacial imaging with automated deep‐learning skull segmentation. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30275

BibTeX
@article{Vu2025,
  author = {Vu, Brian-Tinh Duc and Kamona, Nada and Kim, Yohan and Ng, Jinggang J and Jones, Brandon C and Wehrli, Felix W and Song, Hee Kwon and Bartlett, Scott P and Lee, Hyunyeol and Rajapakse, Chamith S},
  title = {Three contrasts in 3 min: Rapid, high‐resolution, and bone‐selective UTE MRI for craniofacial imaging with automated deep‐learning skull segmentation},
  journal = {Magnetic Resonance in Medicine},
  year = {2025},
  doi = {10.1002/mrm.30275}
}
Kostenlos starten →