Skip to main content
Dryad

Deep learning software and revised 2D model to segment bone in micro-CT scans

Lee, Andrew1; Talluri, Ganesh2; Damani, Manan1; Vera Covarrubias, Brandon1; Hanna, Helena1; Chavez, Jeremy1; Moore, Julian1; Baradarian, Jacob1; Molgaard, Michael1; Nielson, Beau1; Walden, Kalah1; Broderick, Thomas1; Al-Nakkash, Layla1

Published Feb 03, 2026; Updated Feb 04, 2026 on Dryad. https://doi.org/10.5061/dryad.4j0zpc8qq

Data files

Feb 03, 2026 version files 44.44 GB
Feb 04, 2026 version files 44.64 GB

Click names to download individual files Select up to 11 GB of files for zip download

Abstract

Deep learning (DL) enables automated bone segmentation in micro-CT datasets but can struggle to generalize across developmental stages, anatomical regions, and imaging conditions. We present BP-2D-03, which is a revised 2D Bone-Pores segmentation model. It was trained on a new dataset comprising 20 micro-CT scans spanning five mammalian species and 142,960 image patches. To tackle the substantially larger and more varied dataset, we developed a new DL software interface with modules for training (“BONe DLFit”), prediction (“BONe DLPred”), and evaluation (“BONe IoU”). These tools addressed issues with prior pipelines, such as slice-level data leakage, high memory usage, and limited multi-GPU support. BONe’s performance was evaluated through three complementary analyses. First, 5-fold cross-validation of the baseline model (U-Net with ResNet-18 backbone and 256-px patches) assessed the effect of dataset composition on model robustness and stability, showing generally high mean Intersection-over-Union (IoU) across folds and replicates. Second, 30 benchmarking experiments tested how model architecture, encoder backbone, and patch size influence segmentation IoU and computational efficiency. U-Net and UNet++ architectures with simple convolutional backbones (e.g., ResNet-18) achieved the highest predictivity and best performance-efficiency tradeoffs, with top models reaching mean IoU values of ~0.97, whereas transformer-based and atrous-convolution models benefited from larger patches but still underperformed in mean IoU. Third, cross-platform experiments confirmed that BONe produces stable results across different hardware configurations, operating systems, and implementations (Avizo 3D and standalone). Together, these analyses demonstrate that BONe delivers robust baseline performance and reproducible results across platforms.