Separation of two radionuclides in simultaneous 123I/ 99mTc SPECT with artificial neural networks

Masatoshi Ishii, Koichi Ogawa, Tadaki Nakahara, Jun Hashimoto, Atsushi Kubo

Research output: Contribution to journalConference article


This study was carried out to reconstruct quantitative images in simultaneous 123/ 99mTc SPECT. In the 123I/ 99mTc SPECT study the image reconstructed with the counts of primary photons emitted from the radionuclide with low photopeak energy( 99mTc) is distorted by Compton scattered photons originating in the radionuclide with high photopeak energy( 123I). To correct the scattered photons included in the low energy photopeak window in the simultaneous data acquisition, we proposed a method with a neural network at the 1999 IEEE Medical Imaging Conference. In this paper we investigated the performance of our method with Monte Carlo simulations and phantom experiments with a brain phantom and a myocardial phantom. The results showed that our method could separate 99mTc and 123I with an error of about 4% The results promised to enable us to make clinical trials with dual radionuclides.

Original languageEnglish
Article numberM3-85
Pages (from-to)1872-1876
Number of pages5
JournalIEEE Nuclear Science Symposium Conference Record
Publication statusPublished - 2003 Dec 1
Event2003 IEEE Nuclear Science Symposium Conference Record - Nuclear Science Symposium, Medical Imaging Conference - Portland, OR, United States
Duration: 2003 Oct 192003 Oct 25


ASJC Scopus subject areas

  • Radiation
  • Nuclear and High Energy Physics
  • Radiology Nuclear Medicine and imaging

Cite this