Dual-tracer PET image separation using three-dimensional depthwise separable convolution network(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2025年第2期
- Page:
- 160-166
- Research Field:
- 医学影像物理
- Publishing date:
Info
- Title:
- Dual-tracer PET image separation using three-dimensional depthwise separable convolution network
- Author(s):
- TANG Dayang1; 2; HU Debin2; QI Hongliang2; SUN Hao1; HAN Yanjiang3; LI Hanwei2; ZHANG Xinming1; 2; PAN Zhilin2; YU Wenjie1; 2; LU Lijun1; CHEN Hongwen1; 2
- 1. School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China 2. Department of Clinical Engineering, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China 3. PET Center, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China
- Keywords:
- Keywords: positron emission computed tomography dual-tracer imaging image registration depthwise separable convolution network deep learning
- PACS:
- R318；R817
- DOI:
- DOI:10.3969/j.issn.1005-202X.2025.02.004
- Abstract:
- Abstract: Objective To propose a novel method based on three-dimensional depthwise separable convolution network (3D DSN) for the separation of PET images with dual tracers of 18F-FDG and 18F-FAPI. Methods A total of 120 pairs of 18F-FDG and 18F-FAPI PET images of the same patient scanned separately at different time points were collected, and the dual-tracer PET image was generated through simulation. After the image registration of PET images of two tracers for ensuring spatial position matching, the registered PET images were forward-projected to generate sinogram data, and the sinogram data of two tracers were accumulated to obtain mixed sinogram data. Subsequently, the dual-tracer PET image was reconstructed using maximum likelihood expectation maximization and input into a 3D DSN based network for image separation, thereby obtaining PET images of two single tracers. Results Compared with 3D CNN method, the proposed method increased the structure similarity index measure (SSIM) of the separated 18F-FDG images to the real 18F-FDG images by 0.87%, increased the peak signal-to-noise ratio (PSNR) by 11.8%, and reduced the normalized root mean square error (NRMSE) by 52%. The SSIM of the separated 18F-FAPI images to the real 18F-FAPI images increased by 1.1%, PSNR increased by 17.0%, and NRMSE decreased by 51%. Conclusion The proposed method can be effectively applied to simultaneous PET imaging with dual PET tracers, reducing the number of scans and costs in time and money, and providing clinical doctors more accurate and abundant diagnostic information.
Last Update: 2025-01-22