Simultaneous dual-isotope imaging based on an artificial neural network for evaluating myocardial perfusion and fatty acid metabolism

We contrived a scatter correction method based on an artificial neural network (ANN) and applied it to the simultaneous evaluation of myocardial perfusion and fatty acid metabolism in single-photon emission computed tomography (SPECT). The count data of three energy windows were used as inputs of the ANN. The count ratios of the estimated primary-to-total photons for Tc-99m and I-123, which were used to reconstruct Tc-99m and I-123 images, were calculated using the ANN. In a phantom study, single- and dual-isotope imaging with Tc-99m/I-123 and Tl-201/I-123 was performed by means of a cardiac phantom simulating patients with and without obesity. In a human study, five normal volunteers and ten patients with myocardial infarction underwent myocardial perfusion and fatty acid metabolism imaging with single and dual SPECT with combinations of Tc-99m-methoxyisobutylisonitrile/I-123-beta-methyl(p-iodophenyl)pentadecanoic acid (BMIPP) and Tl-201/I-123-BMIPP as tracers. Technetium-99m yielded more homogeneous images than Tl-201 because of the lower degree of photon attenuation, especially in the condition of obese patients, resulting in clearer visualization of the perfusion-metabolism mismatch. Dual Tc-99m/I-123 SPECT offered comparable images with single SPECT in assessing myocardial damage. The method effectively separated Tc-99m and I-123 primary photons and proved applicable to Tc-99m/I-123 dual-isotope myocardial SPECT.