Title :
Limited angle tomography using regularized extrapolation technique
Author :
Yu, Kai-Kou R. ; Yau, Sze-Fong
Author_Institution :
Dept. of Electr. & Electron. Eng., Hong Kong Univ. of Sci. & Technol., Kowloon, Hong Kong
Abstract :
Considers the well-known limited angle or missing cone problem. The authors present an alternative method to extrapolate the missing set of projection data from limited angle of views without prior information of the scanning object, using two-dimensional sampling theory and the result by Rattey and Lindgren which shows that the spectral support of computerised tomography (CT) projection data is bowtie-shaped. A general matrix formulation is developed and the problem is posed as a least square optimization problem. This problem is then implemented by a nonstandard neural network. A novel training algorithm is proposed minimizing a modified error criterion. A computer simulation result is presented to demonstrate the validity of the algorithm
Keywords :
computerised tomography; extrapolation; image reconstruction; matrix algebra; medical image processing; neural nets; optimisation; 2D sampling theory; computerised tomography; error criterion; general matrix formulation; learning algorithm; least square optimization; limited angle tomography; medical diagnostic imaging; missing cone problem; nonstandard neural network; projection data; regularized extrapolation; scanning; Artificial neural networks; Computed tomography; Computer errors; Electron traps; Extrapolation; Fourier transforms; Image reconstruction; Least squares methods; Neural networks; Sampling methods;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344788