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

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 Intersectio..., Dataset collection
The deep learning dataset was assembled from three sources (Table 1). First, we included 11 micro-CT scans of long bones from the North American river otter (Lontra canadensis) that were previously analyzed by Lee et al. (2025). Second, we downloaded three scans of long bones from capybara (Hydrochoerus hydrochaeris; AMNH:Mammals:M-206440), leopard (Panthera pardus; AMNH:Mammals:M-89009), and sea otter (Enhydra lutris; ZMB:Mam:30740) from MorphoSource. Third, we collected six new micro-CT scans from a sample of laboratory mouse (Mus musculus) that is described below.
Forty male C57BL/6 mice (4-wk old) were purchased from Charles River Laboratory (Wilmington, MA, USA) and maintained for 25 weeks. After the mice were euthanized, the limb bones (humerus, radius, ulna, femur, tibia, and fibula) were dissected, fixed in 10% neutral buffered formalin for 24 hours, stored in 70% ethanol. All animal care was conducted in accordance with established guidelines, and all protoco..., # Deep learning software and revised 2D model to segment bone in micro-CT scans

Dataset DOI: [10.5061/dryad.4j0zpc8qq](10.5061/dryad.4j0zpc8qq)

## Description of the data and file structure

### Code and Data

**File: \_BONe_Avizo.zip**

**Description:** contains the Avizo script files used to train models on micro-CT scans (BONe_DLFit), apply deep learning (DL) models to segment micro-CT scans (BONe_DLPred), and compare overlap between reference and predicted segmentations (BONe_IoU). These modules were designed to integrate with Avizo 2024.2 and its Python 3.11.x virtual environment (preliminary testing suggests compatibility with Avizo 2025.1). If needed, the functionality of the modules may be customized by the user by opening the rc, py, and pyscro files in the Python code editor of choice. The rc files control the location and appearance of the modules in the menu of modules. Deep learning functionality is controlled by the py and pyscro files.

**Installation:** The BONe module..., , **Changes after Feb 3, 2026:** 

```
List of updated files:
_BONe_Avizo.zip
_BONe_standalone.zip
_Models.zip
```

Additional features and optimizations were added to the BONe Avizo modules and standalone apps. They have been updated from version 1.0.0 to 1.12.6.

**BONe DLFit 1.12.6**

* (Avizo only) Normalization during volume statistics calculation is more precise and matches normalization used by standalone BONe DLFit as well as of Avizo and standalone BONe DLPred.
* Calculation of volume statistics for normalization uses 70-85% less RAM. The number of scans processed simultaneously was reduced from 16 to 2. RAM pressure was also reduced by using a chunked bitwise exact method to calculate volume mean, standard deviation, minimum, and maximum.
* Calculation of volume statistics no longer runs using an external Python executable, so that code was removed.
* Added versioning to the graphical user interface and metadata.
* Added toggle to switch between shuffling scans before the t...