Application of Self-Organizing Artificial Neural Networks on Simulated Diffusion Tensor Images
Figure 8
The SOFMAT results are investigated, and the determined neighborhood’s coordinates and their related calculated eigenvectors are evaluated. The histogram shows the similarity of the original input and the SOFMAT’s reconstructed tract for orthocrossing trajectory: noise free (a) and SNR = 5 (b). The angular cost function results inform that the input and the output are nearly the same. Here, the input pattern is 150 × 150, where in both cases noise free and SNR = 5, the parameters and are 80 and 40, respectively.
