BoneDat, a database of standardized bone morphology for in silico analyses.

Authors

Henyš P,Kuchař M

Affiliations (3)

  • Institute of New Technologies and Applied Informatics, Faculty of Mechatronics, Informatics and Interdisciplinary Studies, Technical University of Liberec, Liberec, 461 17, Czechia.
  • Institute of New Technologies and Applied Informatics, Faculty of Mechatronics, Informatics and Interdisciplinary Studies, Technical University of Liberec, Liberec, 461 17, Czechia. [email protected].
  • Department of Anatomy, Faculty of Medicine in Hradec Kralove, Hradec Kralove, 500 03, Czechia. [email protected].

Abstract

In silico analysis is key to understanding bone structure-function relationships in orthopedics and evolutionary biology, but its potential is limited by a lack of standardized, high-quality human bone morphology datasets. This absence hinders research reproducibility and the development of reliable computational models. To overcome this, BoneDat has been developed. It is a comprehensive database containing standardized bone morphology data from 278 clinical lumbopelvic CT scans (pelvis and lower spine). The dataset includes individuals aged 16 to 91, balanced by sex across ten age groups. BoneDat provides curated segmentation masks, normalized bone geometry (volumetric meshes), and reference morphology templates organized by sex and age. By offering standardized reference geometry and enabling shape normalization, BoneDat enhances the repeatability and credibility of computational models. It also allows for integrating other open datasets, supporting the training and benchmarking of deep learning models and accelerating their path to clinical use.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.