A New Method for 3D Thinning of Hybrid Shaped Porous Media Using Artificial Intelligence. Application to Trabecular Bone

Abstract

Curve and surface thinning are widely-used skeletonization techniques for modeling objects in three dimensions. In the case of disordered porous media analysis, however, neither is really efficient since the internal geometry of the object is usually composed of both rod and plate shapes. This paper presents an alternative to compute a hybrid shape-dependent skeleton and its application to porous media. The resulting skeleton combines 2D surfaces and 1D curves to represent respectively the plate-shaped and rod-shaped parts of the object. For this purpose, a new technique based on neural networks is proposed: cascade combinations of complex wavelet transform (CWT) and complex-valued artificial neural network (CVANN). The ability of the skeleton to characterize hybrid shaped porous media is demonstrated on a trabecular bone sample. Results show that the proposed method achieves high accuracy rates about 99.78%-99.97%. Especially, CWT (2nd level)-CVANN structure converges to optimum results as high accuracy rate-minimum time consumption.

An approach for tissue density classification in mammographic images using artificial neural network based on wavelet and curvelet transforms

“…The procedure called "training" is ended when ANN, which produces new outputs in line with the new weight coefficients, reaches the desired error value. Using the obtained weight coefficients from this iterative training process, the ANN test procedure is performed through the data which haven't been introduced to the network [16,17].…”