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
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.

深度学习（Deep Learning, DL）可实现显微CT（micro-CT）数据集的自动化骨分割，但在跨发育阶段、解剖区域及成像条件时泛化能力欠佳。本研究提出BP-2D-03，一款优化后的二维骨孔隙分割模型。该模型基于全新数据集训练所得，该数据集包含20组覆盖5种哺乳动物的显微CT扫描结果，以及142960张图像块。为处理规模更大、异质性更强的数据集，我们开发了一套全新的深度学习软件工具集，包含训练模块（"BONe DLFit"）、预测模块（"BONe DLPred"）与评估模块（"BONe IoU"）。这套工具解决了此前流程中存在的诸多问题，例如切片级数据泄露、内存占用过高以及多GPU支持受限等缺陷。我们通过三项互补性分析对BONe的性能开展评估：其一，对基线模型（搭载ResNet-18骨干网络、使用256像素图像块的U-Net）进行5折交叉验证，以探究数据集构成对模型鲁棒性与稳定性的影响，结果显示各折次与重复实验的平均交并比（Intersection-over-Union, IoU）普遍较高；其二，开展30组基准测试实验，分析模型架构、编码器骨干网络以及图像块尺寸对分割交并比与计算效率的影响。结果表明，搭载简单卷积骨干网络（如ResNet-18）的U-Net与UNet++架构实现了最高的预测性能与最优的性能-效率权衡，顶尖模型的平均交并比可达约0.97；而基于Transformer与扩张卷积的模型虽可从更大尺寸的图像块中获益，但平均交并比仍稍逊一筹。其三，跨平台实验证实，BONe可在不同硬件配置、操作系统与实现方式（Avizo 3D与独立程序）下输出稳定的结果。综上，上述分析证明BONe可提供稳定的基准性能，且在不同平台下均可复现实验结果。