Back to Search
Start Over
Deep learning-based attenuation correction method in 99m Tc-GSA SPECT/CT hepatic imaging: a phantom study.
- Source :
-
Radiological physics and technology [Radiol Phys Technol] 2024 Mar; Vol. 17 (1), pp. 165-175. Date of Electronic Publication: 2023 Nov 30. - Publication Year :
- 2024
-
Abstract
- This study aimed to evaluate a deep learning-based attenuation correction (AC) method to generate pseudo-computed tomography (CT) images from non-AC single-photon emission computed tomography images (SPECT <subscript>NC</subscript> ) for AC in <superscript>99m</superscript> Tc-galactosyl human albumin diethylenetriamine pentaacetic acid (GSA) scintigraphy and to reduce patient dosage. A cycle-consistent generative network (CycleGAN) model was used to generate pseudo-CT images. The training datasets comprised approximately 850 liver phantom images obtained from SPECT <subscript>NC</subscript> and real CT images. The training datasets were then input to CycleGAN, and pseudo-CT images were output. SPECT images with real-time CT attenuation correction (SPECT <subscript>CTAC</subscript> ) and pseudo-CT attenuation correction (SPECT <subscript>GAN</subscript> ) were acquired. The difference in liver volume between real CT and pseudo-CT images was evaluated. Total counts and uniformity were then used to evaluate the effects of AC. Additionally, the similarity coefficients of SPECT <subscript>CTAC</subscript> and SPECT <subscript>GAN</subscript> were assessed using a structural similarity (SSIM) index. The pseudo-CT images produced a lower liver volume than the real CT images. SPECT <subscript>CTAC</subscript> exhibited a higher total count than SPECT <subscript>NC</subscript> and SPECT <subscript>GAN</subscript> , which were approximately 60% and 7% lower, respectively. The uniformities of SPECT <subscript>CTAC</subscript> and SPECT <subscript>GAN</subscript> were better than those of SPECT <subscript>NC</subscript> . The mean SSIM value for SPECT <subscript>CTAC</subscript> and SPECT <subscript>GAN</subscript> was 0.97. We proposed a deep learning-based AC approach to generate pseudo-CT images from SPECT <subscript>NC</subscript> images in <superscript>99m</superscript> Tc-GSA scintigraphy. SPECT <subscript>GAN</subscript> with AC using pseudo-CT images was similar to SPECT <subscript>CTAC</subscript> , demonstrating the possibility of SPECT/CT examination with reduced exposure to radiation.<br /> (© 2023. The Author(s), under exclusive licence to Japanese Society of Radiological Technology and Japan Society of Medical Physics.)
Details
- Language :
- English
- ISSN :
- 1865-0341
- Volume :
- 17
- Issue :
- 1
- Database :
- MEDLINE
- Journal :
- Radiological physics and technology
- Publication Type :
- Academic Journal
- Accession number :
- 38032506
- Full Text :
- https://doi.org/10.1007/s12194-023-00762-x