A deep learning-based framework for standardized analysis of trabecular bone compartments from micro-CT imaging data in the mouse tibia

Understanding bone remodeling and disease progression is crucial in preclinical skeletal research, particularly for assessing pharmacological and mechanical interventions in the long bones of murine models. High-resolution micro-computed tomography(micro-CT) imaging enables detailed trabecular bone analysis, but its reproducibility is limited by inconsistent landmarking and non-standardized volume of interest (VOI) definitions. In this study, we introduce a deep learning framework for automated trabecular bone analysis in micro-CT scans from mouse tibiae. The epiphyseal-metaphyseal region is classified into four anatomical compartments, epiphyseal bone, growth plate, primary spongiosa, and secondary spongiosa, using a 2D slice-wise classification model combined with a regional probability distribution method for anatomical landmark detection and standardized VOI extraction. To validate our method, we trained and tested the model on three independent micro-CT datasets comprising a total of 40 bone scans (28,155 2D slices), each annotated by three experts to assess inter- and intra-operator variability, and further assessed its generalizability using an additional external dataset. These datasets encompassed diverse experimental conditions, including pharmacological treatments, mechanical loading, and age-related reduced bone density. Our classification model achieved excellent performances (mean F1-score = 0.92; statistical equivalence within 0.03 mm, p ≤ 0.05) and demonstrated strong generalizability on the external dataset (mean F1-score = 0.97; statistical equivalence within 0.05 mm, p ≤ 0.05). Following compartmental extraction, trabecular bone is segmented within the epiphyseal bone, primary spongiosa, and secondary spongiosa using a deep learning-based model, enabling automated and robust morphometric and statistical analyses across the three trabecular compartments. This automated approach provides a robust and reproducible method for analyzing micro-CT images of the trabecular bone in the mouse tibia, facilitating advancements in preclinical skeletal research.