We investigate the use of different trabecular bone descriptors and advanced machine learning tech niques to complement standard bone mineral density (BMD) measures derived from dual-energy x-ray absorptiometry (DXA) for improving clinical assessment of osteoporotic fracture risk. For this purpose, volumes of interest were extracted from the head, neck, and trochanter of 146 ex vivo proximal femur specimens on multidetector computer tomography. The trabecular bone captured was characterized with (1) statistical moments of the BMD distribution, (2) geometrical features derived from the scaling index method (SIM), and (3) morphometric parameters, such as bone fraction, trabecular thickness, etc. Feature sets comprising DXA BMD and such supplemental features were used to predict the failure load (FL) of the specimens, previously determined through biomechanical testing, with multiregression and support vector regression. Prediction performance was measured by the root mean square error (RMSE); correlation with measured FL was evaluated using the coefficient of determination R². The best prediction performance was achieved by a combination of DXA BMD and SIM-derived geometric features derived from the femoral head (RMSE: 0.869 ± 0.121, R²: 0.68 ± 0.079), which was significantly better than DXA BMD alone (RMSE: 0.948 ± 0.119, R²: 0.61 ± 0.101) (p < 10^-4). For multivariate feature sets, SVR outperformed multiregression (p < 0.05). These results suggest that supplementing standard DXA BMD measurements with sophisticated femoral trabecular bone characterization and supervised learning techniques can significantly improve biomechanical strength prediction in proximal femur specimens.

To develop and characterize a clinically applicable, fast and efficient method for stem cell labeling with ferucarbotran and protamine for depiction with clinical MRI. The hydrodynamic diameter, zeta potential and relaxivities of ferucarbotran and varying concentrations of protamine were measured. Once the optimized ratio was found, human mesenchymal stem cells (MSCs) were labeled at varying incubation times (1–24 h). Viability was assessed via Trypan blue exclusion testing. 150,000 labeled cells in Ficoll solution were imaged with T1-, T2- and T2*-weighted sequences at 3 T, and relaxation rates were calculated. Varying the concentrations of protamine allows for easy modification of the physicochemical properties. Simple incubation with ferucarbotran alone resulted in efficient labeling after 24 h of incubation while assisted labeling with protamine resulted in similar results after only 1 h. Cell viability remained unaffected. R2 and R2* relaxation rates were drastically increased. Electron microscopy confirmed intracellular iron oxide uptake in lysosomes. Relaxation times correlated with results from ICP-AES. Our results show internalization of ferucarbotran can be accelerated in MSCs with protamine, an approved heparin antagonist and potentially clinically applicable uptake-enhancing agent.