Assessment of cortical bone fracture resistance curves by fusing artificial neural networks and linear regression.

Bone injures (BI) represents one of the major health problems, together with cancer and cardiovascular diseases. Assessment of the risks associated with BI is nontrivial since fragility of human cortical bone is varying with age. Due to restrictions for performing experiments on humans, only a limited number of fracture resistance curves (R-curves) for particular ages have been reported in the literature. This study proposes a novel decision support system for the assessment of bone fracture resistance by fusing various artificial intelligence algorithms. The aim was to estimate the R-curve slope, toughness threshold and stress intensity factor using the two input parameters commonly available during a routine clinical examination: patients age and crack length. Using the data from the literature, the evolutionary assembled Artificial Neural Network was developed and used for the derivation of Linear regression (LR) models of R-curves for arbitrary age. Finally, by using the patient (age)-specific LR models and diagnosed crack size one could estimate the risk of bone fracture under given physiological conditions. Compared to the literature, we demonstrated improved performances for estimating nonlinear changes of R-curve slope (R2 = 0.82 vs. R2 = 0.76) and Toughness threshold with ageing (R2 = 0.73 vs. R2 = 0.66).

Finite element analysis of uncommonly large renal arteriovenous malformation--adjacent renal cyst complex.

BACKGROUND: Renal arteriovenous malformation (RAVM) represents abnormal communication between the intrarenal arterial and venous system. The purpose of this study was to investigate hemodynamics and biomechanics quantities which may influence the instability of RAVM and imply clinical complications. METHODS: A detailed 3D reconstruction of RAVM was obtained from the patient CT scans, aortic inlet flow was measured by color-flow Doppler ultrasound, while material characteristics were adopted from the literature. A numerical finite element analysis (FEA) of the blood flow was performed by solving the governing equations for the viscous incompressible flow. The physical quantities calculated at the systolic and diastolic peak moment were velocity, pressure, shear stress and drag forces. RESULTS: We reported a case of a 50-year-old patient with a large RAVM and adjacent renal cyst, who unsuccessfully underwent two attempts of embolization that resulted in the consequent nephrectomy. FEA showed that the cyst had a very low pressure intensity and velocity field (with unstable flow in diastolic peak). For both systolic and diastolic moments, increased values of wall shear stress were found on the places with intensive wall calcification. Unusually high values of drag force which would likely explain the presence of pressure in the cystic formation were found on the infero-medial side where the cyst wall was the thinnest and where the flow streamlines converged. CONCLUSIONS: FEA showed that the hemodynamics of the cyst-RAVM complex was unstable making it prone to rupture. Clinically established diagnosis of imminent rupture together with unfavorable hemodynamics of the lesion consequently made additional attempts of embolization risky and unsuccessful leading to total nephrectomy.

Computer methods for follow-up study of hemodynamic and disease progression in the stented coronary artery by fusing IVUS and X-ray angiography.

Despite a lot of progress in the fields of medical imaging and modeling, problem of estimating the risk of in-stent restenosis and monitoring the progress of the therapy following stenting still remains. The principal aim of this paper was to propose architecture and implementation details of state of the art of computer methods for a follow-up study of disease progression in coronary arteries stented with bare-metal stents. The 3D reconstruction of coronary arteries was performed by fusing X-ray angiography and intravascular ultrasound (IVUS) as the most dominant modalities in interventional cardiology. The finite element simulation of plaque progression was performed by coupling the flow equations with the reaction-diffusion equation applying realistic boundary conditions at the wall. The alignment of baseline and follow-up data was performed automatically by temporal alignment of IVUS electrocardiogram-gated frames. The assessment was performed using three six-month follow-ups of right coronary artery. Simulation results were compared with the ground truth data measured by clinicians. In all three data sets, simulation results indicated the right places as critical. With the obtained difference of 5.89 ± ~4.5% between the clinical measurements and the results of computer simulations, we showed that presented framework is suitable for tracking the progress of coronary disease, especially for comparing face-to-face results and data of the same artery from distinct time periods.