Dynamic PET Imaging Using Dual Texture Features
Purpose: This study aims to explore the impact of adding texture features in dynamic positron emission tomography (PET) reconstruction of imaging results.Methods: We have improved a reconstruction method that combines radiological dual texture features. In this method, multiple short time frames are...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2021.819840/full |
| _version_ | 1818974680156995584 |
|---|---|
| author | Zhanglei Ouyang Zhanglei Ouyang Shujun Zhao Zhaoping Cheng Yanhua Duan Zixiang Chen Na Zhang Dong Liang Zhanli Hu |
| author_facet | Zhanglei Ouyang Zhanglei Ouyang Shujun Zhao Zhaoping Cheng Yanhua Duan Zixiang Chen Na Zhang Dong Liang Zhanli Hu |
| author_sort | Zhanglei Ouyang |
| collection | DOAJ |
| description | Purpose: This study aims to explore the impact of adding texture features in dynamic positron emission tomography (PET) reconstruction of imaging results.Methods: We have improved a reconstruction method that combines radiological dual texture features. In this method, multiple short time frames are added to obtain composite frames, and the image reconstructed by composite frames is used as the prior image. We extract texture features from prior images by using the gray level-gradient cooccurrence matrix (GGCM) and gray-level run length matrix (GLRLM). The prior information contains the intensity of the prior image, the inverse difference moment of the GGCM and the long-run low gray-level emphasis of the GLRLM.Results: The computer simulation results show that, compared with the traditional maximum likelihood, the proposed method obtains a higher signal-to-noise ratio (SNR) in the image obtained by dynamic PET reconstruction. Compared with similar methods, the proposed algorithm has a better normalized mean squared error (NMSE) and contrast recovery coefficient (CRC) at the tumor in the reconstructed image. Simulation studies on clinical patient images show that this method is also more accurate for reconstructing high-uptake lesions.Conclusion: By adding texture features to dynamic PET reconstruction, the reconstructed images are more accurate at the tumor. |
| first_indexed | 2024-12-20T15:43:54Z |
| format | Article |
| id | doaj.art-f488e8b76e084c81a866644e251d53ad |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-12-20T15:43:54Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-f488e8b76e084c81a866644e251d53ad2022-12-21T19:35:04ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882022-01-011510.3389/fncom.2021.819840819840Dynamic PET Imaging Using Dual Texture FeaturesZhanglei Ouyang0Zhanglei Ouyang1Shujun Zhao2Zhaoping Cheng3Yanhua Duan4Zixiang Chen5Na Zhang6Dong Liang7Zhanli Hu8School of Physics, Zhengzhou University, Zhengzhou, ChinaLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaSchool of Physics, Zhengzhou University, Zhengzhou, ChinaDepartment of PET/CT, The First Affiliated Hospital of Shandong First Medical University, Shandong Provincial Qianfoshan Hospital, Jinan, ChinaDepartment of PET/CT, The First Affiliated Hospital of Shandong First Medical University, Shandong Provincial Qianfoshan Hospital, Jinan, ChinaLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaPurpose: This study aims to explore the impact of adding texture features in dynamic positron emission tomography (PET) reconstruction of imaging results.Methods: We have improved a reconstruction method that combines radiological dual texture features. In this method, multiple short time frames are added to obtain composite frames, and the image reconstructed by composite frames is used as the prior image. We extract texture features from prior images by using the gray level-gradient cooccurrence matrix (GGCM) and gray-level run length matrix (GLRLM). The prior information contains the intensity of the prior image, the inverse difference moment of the GGCM and the long-run low gray-level emphasis of the GLRLM.Results: The computer simulation results show that, compared with the traditional maximum likelihood, the proposed method obtains a higher signal-to-noise ratio (SNR) in the image obtained by dynamic PET reconstruction. Compared with similar methods, the proposed algorithm has a better normalized mean squared error (NMSE) and contrast recovery coefficient (CRC) at the tumor in the reconstructed image. Simulation studies on clinical patient images show that this method is also more accurate for reconstructing high-uptake lesions.Conclusion: By adding texture features to dynamic PET reconstruction, the reconstructed images are more accurate at the tumor.https://www.frontiersin.org/articles/10.3389/fncom.2021.819840/fulldynamic PETtexture featuregray level-gradient cooccurrence matrix (GGCM)gray-level run length matrix (GLRLM)tumor |
| spellingShingle | Zhanglei Ouyang Zhanglei Ouyang Shujun Zhao Zhaoping Cheng Yanhua Duan Zixiang Chen Na Zhang Dong Liang Zhanli Hu Dynamic PET Imaging Using Dual Texture Features Frontiers in Computational Neuroscience dynamic PET texture feature gray level-gradient cooccurrence matrix (GGCM) gray-level run length matrix (GLRLM) tumor |
| title | Dynamic PET Imaging Using Dual Texture Features |
| title_full | Dynamic PET Imaging Using Dual Texture Features |
| title_fullStr | Dynamic PET Imaging Using Dual Texture Features |
| title_full_unstemmed | Dynamic PET Imaging Using Dual Texture Features |
| title_short | Dynamic PET Imaging Using Dual Texture Features |
| title_sort | dynamic pet imaging using dual texture features |
| topic | dynamic PET texture feature gray level-gradient cooccurrence matrix (GGCM) gray-level run length matrix (GLRLM) tumor |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2021.819840/full |
| work_keys_str_mv | AT zhangleiouyang dynamicpetimagingusingdualtexturefeatures AT zhangleiouyang dynamicpetimagingusingdualtexturefeatures AT shujunzhao dynamicpetimagingusingdualtexturefeatures AT zhaopingcheng dynamicpetimagingusingdualtexturefeatures AT yanhuaduan dynamicpetimagingusingdualtexturefeatures AT zixiangchen dynamicpetimagingusingdualtexturefeatures AT nazhang dynamicpetimagingusingdualtexturefeatures AT dongliang dynamicpetimagingusingdualtexturefeatures AT zhanlihu dynamicpetimagingusingdualtexturefeatures |