Abstract
Abstract Introduction The mechanical competence parameter (MCP) of the trabecular bone is a parameter that merges the volume fraction, connectivity, tortuosity and Young modulus of elasticity, to provide a single measure of the trabecular bone structural quality. Methods As the MCP is estimated for 3D images and the Young modulus simulations are quite consuming, in this paper, an alternative approach to estimate the MCP based on artificial neural network (ANN) is discussed considering as the training set a group of 23 in vitro vertebrae and 12 distal radius samples obtained by microcomputed tomography (μCT), and 83 in vivo distal radius magnetic resonance image samples (MRI). Results It is shown that the ANN was able to predict with very high accuracy the MCP for 29 new samples, being 6 vertebrae and 3 distal radius bones by μCT and 20 distal radius bone by MRI. Conclusion There is a strong correlation (R2 = 0.97) between both techniques and, despite the small number of testing samples, the Bland-Altman analysis shows that ANN is within the limits of agreement to estimate the MCP.
Highlights
The mechanical competence parameter (MCP) of the trabecular bone is a parameter that merges the volume fraction, connectivity, tortuosity and Young modulus of elasticity, to provide a single measure of the trabecular bone structural quality
MCP is a parameter introduced by Roque et al (2013a) to provide a way to grade the trabecular bone fragility based on volume fraction, connectivity, tortuosity and elasticity, four fundamental quantities
The results presented here have shown the potentiality of the artificial neural network (ANN) to estimate the MCP taking into account different bone sample sites, distinct imagery devices and the subject form as in vivo or in vitro
Summary
Osteoporosis is a prevalent disease among the elderly population and due to the increase in life expectancy it is becoming a public health problem with very high cost to both public and private health systems (Dimai et al, 2012). The results have shown a good qualitative agreement compared with experimental results published previously In this regard, in a previous study (Filletti and Roque, 2015), the authors investigated the application of an ANN to predict the MCP for 20 magnetic resonance image (MRI) samples based on a training set of 83 in vivo distal radius MRI samples. While the paper Filletti and Roque (2015) had only distal radius bone samples with MRI, in this paper it is shown that the ANN can estimate the MCP for a more general case, including samples that originate from different bone sites and different imaging techniques. Once the ANN is trained, it will provide a simple, accurate and faster method to estimate the MCP, avoiding PCA, which is a much more laborious technique
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
