Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction
Abstract Purpose The aim of this study is to convert low-dose PET (L-PET) images to full-dose PET (F-PET) images based on our Diffused Multi-scale Generative Adversarial Network (DMGAN) to offer a potential balance between reducing radiation exposure and maintaining diagnostic performance. Methods T...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | BioMedical Engineering OnLine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12938-025-01348-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861707379834880 |
|---|---|
| author | Xiang Yu Daoyan Hu Qiong Yao Yu Fu Yan Zhong Jing Wang Mei Tian Hong Zhang |
| author_facet | Xiang Yu Daoyan Hu Qiong Yao Yu Fu Yan Zhong Jing Wang Mei Tian Hong Zhang |
| author_sort | Xiang Yu |
| collection | DOAJ |
| description | Abstract Purpose The aim of this study is to convert low-dose PET (L-PET) images to full-dose PET (F-PET) images based on our Diffused Multi-scale Generative Adversarial Network (DMGAN) to offer a potential balance between reducing radiation exposure and maintaining diagnostic performance. Methods The proposed method includes two modules: the diffusion generator and the u-net discriminator. The goal of the first module is to get different information from different levels, enhancing the generalization ability of the generator to the image and improving the stability of the training. Generated images are inputted into the u-net discriminator, extracting details from both overall and specific perspectives to enhance the quality of the generated F-PET images. We conducted evaluations encompassing both qualitative assessments and quantitative measures. In terms of quantitative comparisons, we employed two metrics, structure similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) to evaluate the performance of diverse methods. Results Our proposed method achieved the highest PSNR and SSIM scores among the compared methods, which improved PSNR by at least 6.2% compared to the other methods. Compared to other methods, the synthesized full-dose PET image generated by our method exhibits a more accurate voxel-wise metabolic intensity distribution, resulting in a clearer depiction of the epilepsy focus. Conclusions The proposed method demonstrates improved restoration of original details from low-dose PET images compared to other models trained on the same datasets. This method offers a potential balance between minimizing radiation exposure and preserving diagnostic performance. |
| format | Article |
| id | doaj-art-2b6da8d81a9340d8959bd00fda7e5648 |
| institution | Kabale University |
| issn | 1475-925X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj-art-2b6da8d81a9340d8959bd00fda7e56482025-02-09T12:47:33ZengBMCBioMedical Engineering OnLine1475-925X2025-02-0124111610.1186/s12938-025-01348-xDiffused Multi-scale Generative Adversarial Network for low-dose PET images reconstructionXiang Yu0Daoyan Hu1Qiong Yao2Yu Fu3Yan Zhong4Jing Wang5Mei Tian6Hong Zhang7Polytechnic Institute, Zhejiang UniversityThe College of Biomedical Engineering and Instrument Science of Zhejiang UniversityDepartment of Nuclear Medicine and Medical PET Center, The Second Affiliated Hospital of Zhejiang University School of MedicineCollege of Information Science and Electronic Engineering, Zhejiang UniversityDepartment of Nuclear Medicine and Medical PET Center, The Second Affiliated Hospital of Zhejiang University School of MedicineDepartment of Nuclear Medicine and Medical PET Center, The Second Affiliated Hospital of Zhejiang University School of MedicineHuman Phenome Institute, Fudan UniversityThe College of Biomedical Engineering and Instrument Science of Zhejiang UniversityAbstract Purpose The aim of this study is to convert low-dose PET (L-PET) images to full-dose PET (F-PET) images based on our Diffused Multi-scale Generative Adversarial Network (DMGAN) to offer a potential balance between reducing radiation exposure and maintaining diagnostic performance. Methods The proposed method includes two modules: the diffusion generator and the u-net discriminator. The goal of the first module is to get different information from different levels, enhancing the generalization ability of the generator to the image and improving the stability of the training. Generated images are inputted into the u-net discriminator, extracting details from both overall and specific perspectives to enhance the quality of the generated F-PET images. We conducted evaluations encompassing both qualitative assessments and quantitative measures. In terms of quantitative comparisons, we employed two metrics, structure similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) to evaluate the performance of diverse methods. Results Our proposed method achieved the highest PSNR and SSIM scores among the compared methods, which improved PSNR by at least 6.2% compared to the other methods. Compared to other methods, the synthesized full-dose PET image generated by our method exhibits a more accurate voxel-wise metabolic intensity distribution, resulting in a clearer depiction of the epilepsy focus. Conclusions The proposed method demonstrates improved restoration of original details from low-dose PET images compared to other models trained on the same datasets. This method offers a potential balance between minimizing radiation exposure and preserving diagnostic performance.https://doi.org/10.1186/s12938-025-01348-xPositron emission tomographyDeep learningImage reconstructionLow-dose PET |
| spellingShingle | Xiang Yu Daoyan Hu Qiong Yao Yu Fu Yan Zhong Jing Wang Mei Tian Hong Zhang Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction BioMedical Engineering OnLine Positron emission tomography Deep learning Image reconstruction Low-dose PET |
| title | Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction |
| title_full | Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction |
| title_fullStr | Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction |
| title_full_unstemmed | Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction |
| title_short | Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction |
| title_sort | diffused multi scale generative adversarial network for low dose pet images reconstruction |
| topic | Positron emission tomography Deep learning Image reconstruction Low-dose PET |
| url | https://doi.org/10.1186/s12938-025-01348-x |
| work_keys_str_mv | AT xiangyu diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction AT daoyanhu diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction AT qiongyao diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction AT yufu diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction AT yanzhong diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction AT jingwang diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction AT meitian diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction AT hongzhang diffusedmultiscalegenerativeadversarialnetworkforlowdosepetimagesreconstruction |