automated-joint-space-detection-improves-bone-segmentation-accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Quantitative description of complex anatomical structures remains challenging due to the expertise necessary for manual segmentation, labor, and ...

Thermo Fisher Scientific

Biomaterial for tissue engineering is a topic of huge progress with a recent surge in fabrication and characterization advances. Biomaterials for tissue engineering applications or as scaffolds depend on various parameters such as fabrication technology, porosity, pore size, mechanical strength, and surface available for cell attachment. To serve the function of the scaffold, the porous biomaterial should have enough mechanical strength to aid in tissue engineering. With a new manufacturing technology, we have obtained high strength materials by optimizing a few processing parameters such as pressure, temperature, and dwell time, yielding the monolith with porosity in the range of 80%⁻93%. The three-dimensional interconnectivity of the porous media through scales for the newly manufactured biomaterial has been investigated using newly developed 3D correlative and multi-modal imaging techniques. Multiscale X-ray tomography, FIB-SEM Slice &amp; View stacking, and high-resolution STEM-EDS electronic tomography observations have been combined allowing quantification of morphological and geometrical spatial distributions of the multiscale porous network through length scales spanning from tens of microns to less than a nanometer. The spatial distribution of the wall thickness has also been investigated and its possible relationship with pore connectivity and size distribution has been studied.

Fabrication and Multiscale Structural Properties of Interconnected Porous Biomaterial for Tissue Engineering by Freeze Isostatic Pressure (FIP).

Quantitative description of complex anatomical structures remains challenging due to the expertise necessary for manual segmentation, labor, and interobserver variability. To overcome this, automated detection of specific landmarks can be provided by digital image analysis techniques including deep learning (DL) models. To this end, we undertook supervised automated analysis of micro-computed tomography (micro-CT) datasets of murine hindpaws and forepaws (30-33 bones). Advancing beyond previously published semi-automated (SA) marker-based watershed algorithms, we added structure enhancement, tensor voting, and output dilation to identify joint spaces. Segmentation was enhanced by the use of a DL joint space prediction model (3D U-Net architecture, ResNet-18 backbone) using wild-type (WT) hindpaw labels as ground truth. Prediction was then extended to hindpaws (52.4% in test group) and forepaws from WT and tumor necrosis factor transgenic (TNF-Tg) mice with inflammatory-erosive arthritis of both sexes across age. Segmentation accuracy improved dramatically using the DL methodology (WT male: SA 79.39±5.73% vs DL 98.16±1.47%, ; WT female: SA 79.16±4.84% vs DL 99.19±1.63%, ). Accuracy declined with increased disease severity and age in TNF-Tg mice (TNF-Tg male 93.54±4.73%, female 91.81±2.80%, ≤). Subsequent testing in forepaws also displayed progressive reduction in accuracy with increasing arthritic severity (i.e., WT 87.29±2.07%, TNF-Tg male 72.65±11.70%, ). Overall, this supervised automated model outperforms recent SA approaches in healthy joints to enhance investigation of complex bone anatomy. Although flexible application to novel and disease-modified datasets demonstrates deprecated performance, utilization may nonetheless catalyze structure-specific segmentation model development.

Article	Year
Fabrication and Multiscale Structural Properties of Interconnected Porous Biomaterial for Tissue Engineering by Freeze Isostatic Pressure (FIP). Journal of functional biomaterials\| PubMed ID: 30149507	2018
Automated Joint Space Detection Improves Bone Segmentation Accuracy. bioRxiv : the preprint server for biology\| PubMed ID: 40654621	2025

Daniel Lichau

Biography

JoVE Journal Publications

Other Publications