EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Segmentation of cortical bone, trabecular bone, and medullary pores from micro‐ CT images using 2D and 3D deep learning models

Andrew H Lee iD, Julian M Moore, Brandon Vera Covarrubias, Leigha M Lynch iD

The Anatomical Record · 2025

DOI: 10.1002/ar.25633 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Anatomical Record, 2025. Verfasst von Andrew H Lee und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anatomy, College of Graduate Studies, Midwestern University, Glendale, Arizona, USA. Hauptthemen laut MEDLINE: X-Ray Microtomography, Deep Learning, Cancellous Bone, Cortical Bone. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computed tomography (CT) enables rapid imaging of large‐scale studies of bone, but those datasets typically require manual segmentation, which is time‐consuming and prone to error. Convolutional neural networks (CNNs) offer an automated solution, achieving superior performance on image data. In this methodology‐focused paper, we used CNNs to train segmentation models from scratch on 2D and 3D patches from micro‐CT scans of otter long bones. These new models, collectively called BONe (Bone One‐shot Network), aimed to be fast and accurate, and we expected enhanced results from 3D training due to better spatial context. Contrary to expectations, 2D models performed slightly better than 3D models in labeling details such as thin trabecular bone. Although lacking in some detail, 3D models appeared to generalize better and predict smoother internal surfaces than 2D models. However, the massive computational costs of 3D models limit their scalability and practicality, leading us to recommend 2D models for bone segmentation. BONe models showed potential for broader applications with variation in performance across species and scan quality. Notably, BONe models demonstrated promising results on skull segmentation, suggesting their potential utility beyond long bones with further refinement and fine‐tuning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

X-Ray MicrotomographyDeep LearningCancellous BoneCortical BoneImaging, Three-DimensionalAnimalsNeural Networks, Computer

Stichwörter der Autor:innen

AvizoU‐Netconvolutional neural netriver otter

Autor:innen und Institutionen

  • Department of Anatomy, College of Graduate Studies, Midwestern University, Glendale, Arizona, USA.
  • College of Veterinary Medicine, Midwestern University, Glendale, Arizona, USA.
  • Arizona College of Osteopathic Medicine, Midwestern University, Glendale, Arizona, USA.

ORCID-Profile: Andrew H Lee, Leigha M Lynch

Zitieren

APA

Lee, A. H., Moore, J. M., Covarrubias, B. V., & Lynch, L. M. (2025). Segmentation of cortical bone, trabecular bone, and medullary pores from micro‐ CT images using 2D and 3D deep learning models. The Anatomical Record. https://doi.org/10.1002/ar.25633

Vancouver

Lee AH, Moore JM, Covarrubias BV, Lynch LM. Segmentation of cortical bone, trabecular bone, and medullary pores from micro‐ CT images using 2D and 3D deep learning models. The Anatomical Record. 2025. doi:10.1002/ar.25633

BibTeX
@article{Lee2025,
  author = {Lee, Andrew H and Moore, Julian M and Covarrubias, Brandon Vera and Lynch, Leigha M},
  title = {Segmentation of cortical bone, trabecular bone, and medullary pores from micro‐ CT images using 2D and 3D deep learning models},
  journal = {The Anatomical Record},
  year = {2025},
  doi = {10.1002/ar.25633}
}
Kostenlos starten →