Scholars@Duke publication: Artificial Neural Networks for SPECT Image Reconstruction with Optimized Weighted Backprojection

Artificial Neural Networks for SPECT Image Reconstruction with Optimized Weighted Backprojection

Conferences

Floyd, CE; Bowsher, JE; Munley, MT; Tourassi, GD; Garg, S; Baydush, AH; Lo, JY; Coleman, RE

Published in: Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991

January 1, 1991

An artificial neural network has been developed to reconstruct quantitative Single Photon Emission Computed Tomographic (SPECT) images. The network is trained using known projection-image pairs containing Poission noise to learn a shift-invariant weighting (filter) which minimizes the mean squared error between the reconstructed image and the sample image. Once trained, The trained network produces a reconstructed image as its output when projection data are presented to its input. Supervised training with a modified delta rule was used to train this two layer neural network having a backpropagation architecture with one hidden layer (the filtered projection). The system was trained for noise levels representative of 1000, 10k, and 1M counts per slice. The Fourier transform of the filtered projection (for an impulse function) is compared with the ramp filter used with backprojection.

Duke Scholars

Author Joseph Yuan-Chieh Lo Radiology

Altmetric Attention Stats

Dimensions Citation Stats

Published In

Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991

DOI

10.1109/nssmic.1991.259306

Publication Date

January 1, 1991

Start / End Page

2184 / 2188

Citation

APA

Chicago

ICMJE

MLA

NLM

Floyd, C. E., Bowsher, J. E., Munley, M. T., Tourassi, G. D., Garg, S., Baydush, A. H., … Coleman, R. E. (1991). Artificial Neural Networks for SPECT Image Reconstruction with Optimized Weighted Backprojection. In Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991 (pp. 2184–2188). https://doi.org/10.1109/nssmic.1991.259306

Floyd, C. E., J. E. Bowsher, M. T. Munley, G. D. Tourassi, S. Garg, A. H. Baydush, J. Y. Lo, and R. E. Coleman. “Artificial Neural Networks for SPECT Image Reconstruction with Optimized Weighted Backprojection.” In Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991, 2184–88, 1991. https://doi.org/10.1109/nssmic.1991.259306.

Floyd CE, Bowsher JE, Munley MT, Tourassi GD, Garg S, Baydush AH, et al. Artificial Neural Networks for SPECT Image Reconstruction with Optimized Weighted Backprojection. In: Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991. 1991. p. 2184–8.

Floyd, C. E., et al. “Artificial Neural Networks for SPECT Image Reconstruction with Optimized Weighted Backprojection.” Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991, 1991, pp. 2184–88. Scopus, doi:10.1109/nssmic.1991.259306.

Floyd CE, Bowsher JE, Munley MT, Tourassi GD, Garg S, Baydush AH, Lo JY, Coleman RE. Artificial Neural Networks for SPECT Image Reconstruction with Optimized Weighted Backprojection. Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991. 1991. p. 2184–2188.

Published In

Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference NSS Mic 1991

DOI

10.1109/nssmic.1991.259306

Publication Date

January 1, 1991

Start / End Page

2184 / 2188