Improved rotational invariance for statistical inverse in electrical impedance tomography

Author

Lahtinen, Jani ; Martinsen, Tomas ; Lampinen, Jouko

Author_Institution

Lab. of Comput. Eng., Helsinki Univ. of Technol., Espoo, Finland

Volume

2

fYear

2000

fDate

2000

Firstpage

154

Abstract

In this paper we show that rotational invariance can be improved in a neural network based electrical impedance tomography (EIT) reconstruction approach by a suitably chosen permutation of the input data. The input space is partitioned to nonoverlapping sectors, and the input signal is permuted so that it lies in one sector independent of the original rotation angle. We demonstrate the advantages of the method with computer simulations. The proposed approach yields better results in the inverse problem, and allows use of smaller networks with fewer training samples

Keywords

Computerised tomography; Electric impedance imaging; Image reconstruction; Neural nets; Statistical analysis; electrical impedance tomography; improved rotational invariance; neural network based EIT reconstruction; nonoverlapping sectors; statistical inverse; Conductivity measurement; Current measurement; Electrodes; Image reconstruction; Inverse problems; Neural networks; Space technology; Surface impedance; Surface reconstruction; Tomography;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.857890

Filename

857890