Pre-reconstruction restoration of SPECT projection images by a neural network
- Univ. of Houston, TX (United States). Dept. of Electrical Engineering
In single photon emission computed tomography (SPECT) the projection images obtained at view angles surrounding the patient are degraded due to the geometric response of the imaging system (a spatially-variant blur), Compton scatter, Poisson noise, and other factors. Various methods have been proposed for compensating for the spatially varying geometric response of the camera. In this study the authors examine restoration of SPECT projection images using an artificial neural network. A three layer feed-forward neural network is trained to compute the spatially-variant standard deviations of a symmetric Gaussian blur. A Hopfield network is then used to restore the projection images in which the restoration problem is formulated as a minimization of an error function of the network. Results from applying this restoration procedure on SPECT projection images are presented and the resulting SPECT reconstruction are analyzed.
- OSTI ID:
- 6906829
- Report Number(s):
- CONF-931051-; CODEN: IETNAE
- Journal Information:
- IEEE Transactions on Nuclear Science (Institute of Electrical and Electronics Engineers); (United States), Vol. 41:4PT1; Conference: NSS-MIC '93: nuclear science symposium and medical imaging conference, San Francisco, CA (United States), 30 Oct - 6 Nov 1993; ISSN 0018-9499
- Country of Publication:
- United States
- Language:
- English
Similar Records
High-speed reconstruction of spect images with a tailored piecewise neural network
The parallel implementation of a backpropagation neural network and its applicability to SPECT image reconstruction
Related Subjects
IMAGES
CORRECTIONS
SINGLE PHOTON EMISSION COMPUTED TOMOGRAPHY
NEURAL NETWORKS
IMAGE PROCESSING
OPTIMIZATION
QUALITY CONTROL
COMPUTERIZED TOMOGRAPHY
CONTROL
DIAGNOSTIC TECHNIQUES
EMISSION COMPUTED TOMOGRAPHY
PROCESSING
TOMOGRAPHY
550601* - Medicine- Unsealed Radionuclides in Diagnostics