Resolution and quality enhancement of SPECT cerebral blood flow images using Pix2pix deep learning.

Journal: Annals of nuclear medicine
Published Date: Nov 13, 2025

Abstract

BACKGROUND: Cerebral blood flow (CBF) imaging can be performed using SPECT with 123I-IMP; however, its spatial resolution and image quality are inferior to those of PET-CBF imaging using labeled water. This study aimed to enhance the resolution and image quality of SPECT-CBF images using the pix2pix machine learning framework. METHODS: Seventy-three patients with suspected cerebral ischemia underwent CBF imaging using SPECT (Symbia, with 123I-IMP) and PET (mCT and Vision, with O-15-labeled gas). Image reconstruction was performed using OSEM for PET and Flash3D for SPECT. The SPECT and PET images were coregistered using SPM12, and a pix2pix model was trained using SPECT-CBF images as input and PET-CBF images as the target, with 43 cases used for training and 15 for testing. P2P-SPECT-CBF images were then generated for 15 cases for validation. Visual assessment on a 5-point scale, structural similarity index measure (SSIM), and region-of-interest (ROI)-based quantitative analysis were performed to evaluate image similarity and accuracy. RESULTS: The P2P-SPECT-CBF images demonstrated improved visual similarity to PET images, with an average score of 4.2 and 3.5 in open and blind assessments, respectively. The SSIM value of conventional SPECT images compared to PET was 0.79, while that of P2P images was 0.86 and those were significantly different, indicating enhanced structural similarity. In ROI analysis, the correlation between SPECT and PET CBF values was y = 0.13 + 0.63x, r = 0.77 (p < 0.01). The correlation between P2P-SPECT and PET was y = 0.10 + 0.65x, r = 0.78 (p < 0.01), and between P2P-SPECT and SPECT, the relationship was y = 0.01 + 0.89x, r = 0.86 (p < 0.01). CONCLUSION: The proposed method generated P2P-SPECT-CBF images with image contrast closely resembling that of PET-CBF, while preserving the quantitative properties of SPECT-CBF.

Authors

  • Nobuyuki Kudomi
    Department of Medical Physics, Faculty of Medicine, Kagawa University, Ikenobe 1750-1, Miki-Cho, Kita-Gun, Takamatsu, Kagawa, 761-0793, Japan. [email protected].
  • Katsuya Mitamura
    Department of Radiology, Faculty of Medicine, Kagawa University, Mikicho, Kagawa, Japan.
  • Yukito Maeda
    Department of Clinical Radiology, Kagawa University Hospital, Mikicho, Kagawa, Japan.
  • Mitsumasa Murao
    Department of Radiology, Faculty of Medicine, Kagawa University, Mikicho, Kagawa, Japan.
  • Masatoshi Morimoto
    Department of Clinical Radiology, Kagawa University Hospital, Mikicho, Kagawa, Japan.
  • Akihiro Ohishi
    Department of Clinical Radiology, Kagawa University Hospital, Mikicho, Kagawa, Japan.
  • Keigo Ohmori
    Department of Clinical Radiology, Kagawa University Hospital, Mikicho, Kagawa, Japan.
  • Takashi Norikane
    Department of Radiology, Faculty of Medicine, Kagawa Univerisity, Takamatsu, Japan.
  • Yuri Manabe
    Department of Radiology, Faculty of Medicine, Kagawa University, Mikicho, Kagawa, Japan.
  • Yuka Yamamoto
    Department of Radiology, Faculty of Medicine, Kagawa University, Mikicho, Kagawa, Japan.
  • Yoshihiro Nishiyama
    Department of Radiology, Faculty of Medicine, Kagawa University, Mikicho, Kagawa, Japan.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals