Neural network approach for Compton-scattering imaging

Jiajun Wang, Yuanmei Wang, Zheru Chi

Research output: Journal article publicationJournal articleAcademic researchpeer-review


The problem of image reconstruction with Compton-scattering spectral data is an ill-posed problem, and the measurement error may be seriously amplified in the reconstruction result. For a stable solution, some kinds of a priori models of the problem should be incorporated into the process of reconstruction. Lee et al. [IEEE. Trans. Nucl. Sci. 40, 2049 (1993)] have proposed a continuous model with binary line processes. Owing to the coexistence of the continuous variable and the binary variable, the commonly used optimization methods for problems with continuous variables cannot be used in this case, and therefore a coupled-gradient artificial neural network was proposed for this mixed-integer problem. By introducing two interacting parts (with one part for the continuous variable and the other for the binary line processes) into the network, and by defining the appropriate energy function and dynamics, high-quality solutions were obtained upon convergence of the dynamics. Some simulated results are presented.
Original languageEnglish
Pages (from-to)2297-2301
Number of pages5
JournalJournal of the Optical Society of America A: Optics and Image Science, and Vision
Issue number9
Publication statusPublished - 1 Jan 1998

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Neural network approach for Compton-scattering imaging'. Together they form a unique fingerprint.

Cite this