Distributed vector processing of the S-transform for medical applications
R.A. Brown, Hongmei Zhu, Joseph Ross Mitchell · 2003
The recently developed Stockwell transform (ST) combines features of the Fourier and Wavelet transforms; it reveals frequency variation over both space and time. It is a potentially powerful tool that can be applied to medical image processing including tissue texture analysis and noise filtering. However, calculation of the ST is computationally intensive, making conventional implementations too slow for medical applications. This problem was addressed with a Fast Fourier transform implementation for Motorola's AltiVec vector processor and a distributed processing system with the goal of creating a flexible system utilizing existing hardware and standards.