Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images

Abstract Purpose Total-body dynamic positron emission tomography (PET) imaging with total-body coverage and ultrahigh sensitivity has played an important role in accurate tracer kinetic analyses in physiology, biochemistry, and pharmacology. However, dynamic PET scans typically entail prolonged dura...

Full description

Saved in:
Bibliographic Details
Main Authors: Qianyi Yang, Wenbo Li, Zhenxing Huang, Zixiang Chen, Wenjie Zhao, Yunlong Gao, Xinlan Yang, Yongfeng Yang, Hairong Zheng, Dong Liang, Jianjun Liu, Ruohua Chen, Zhanli Hu
Format: Article
Language:English
Published: SpringerOpen 2024-11-01
Series:EJNMMI Physics
Subjects:
Online Access:https://doi.org/10.1186/s40658-024-00698-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846171605490728960
author Qianyi Yang
Wenbo Li
Zhenxing Huang
Zixiang Chen
Wenjie Zhao
Yunlong Gao
Xinlan Yang
Yongfeng Yang
Hairong Zheng
Dong Liang
Jianjun Liu
Ruohua Chen
Zhanli Hu
author_facet Qianyi Yang
Wenbo Li
Zhenxing Huang
Zixiang Chen
Wenjie Zhao
Yunlong Gao
Xinlan Yang
Yongfeng Yang
Hairong Zheng
Dong Liang
Jianjun Liu
Ruohua Chen
Zhanli Hu
author_sort Qianyi Yang
collection DOAJ
description Abstract Purpose Total-body dynamic positron emission tomography (PET) imaging with total-body coverage and ultrahigh sensitivity has played an important role in accurate tracer kinetic analyses in physiology, biochemistry, and pharmacology. However, dynamic PET scans typically entail prolonged durations ( $$\:\ge\:$$ 60 minutes), potentially causing patient discomfort and resulting in artifacts in the final images. Therefore, we propose a dynamic frame prediction method for total-body PET imaging via deep learning technology to reduce the required scanning time. Methods On the basis of total-body dynamic PET data acquired from 13 subjects who received [68Ga]Ga-FAPI-04 (68Ga-FAPI) and 24 subjects who received [68Ga]Ga-PSMA-11 (68Ga-PSMA), we propose a bidirectional dynamic frame prediction network that uses the initial and final 10 min of PET imaging data (frames 1–6 and frames 25–30, respectively) as inputs. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were employed as evaluation metrics for an image quality assessment. Moreover, we calculated parametric images (68Ga-FAPI: $$\:{K}_{1}$$ , 68Ga-PSMA: $$\:{K}_{i}$$ ) based on the supplemented sequence data to observe the quantitative accuracy of our approach. Regions of interest (ROIs) and statistical analyses were utilized to evaluate the performance of the model. Results Both the visual and quantitative results illustrate the effectiveness of our approach. The generated dynamic PET images yielded PSNRs of 36.056 ± 0.709 dB for the 68Ga-PSMA group and 33.779 ± 0.760 dB for the 68Ga-FAPI group. Additionally, the SSIM reached 0.935 ± 0.006 for the 68Ga-FAPI group and 0.922 ± 0.009 for the 68Ga-PSMA group. By conducting a quantitative analysis on the parametric images, we obtained PSNRs of 36.155 ± 4.813 dB (68Ga-PSMA, $$\:{K}_{1}$$ ) and 43.150 ± 4.102 dB (68Ga-FAPI, $$\:{K}_{i}$$ ). The obtained SSIM values were 0.932 ± 0.041 (68Ga-PSMA) and 0.980 ± 0.011 (68Ga-FAPI). The ROI analysis conducted on our generated dynamic PET sequences also revealed that our method can accurately predict temporal voxel intensity changes, maintaining overall visual consistency with the ground truth. Conclusion In this work, we propose a bidirectional dynamic frame prediction network for total-body 68Ga-PSMA and 68Ga-FAPI PET imaging with a reduced scan duration. Visual and quantitative analyses demonstrated that our approach performed well when it was used to predict one-hour dynamic PET images. https://github.com/OPMZZZ/BDF-NET .
format Article
id doaj-art-8aac35c7c6a84c8ca535d5c9a20e8658
institution Kabale University
issn 2197-7364
language English
publishDate 2024-11-01
publisher SpringerOpen
record_format Article
series EJNMMI Physics
spelling doaj-art-8aac35c7c6a84c8ca535d5c9a20e86582024-11-10T12:43:01ZengSpringerOpenEJNMMI Physics2197-73642024-11-0111112010.1186/s40658-024-00698-0Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET imagesQianyi Yang0Wenbo Li1Zhenxing Huang2Zixiang Chen3Wenjie Zhao4Yunlong Gao5Xinlan Yang6Yongfeng Yang7Hairong Zheng8Dong Liang9Jianjun Liu10Ruohua Chen11Zhanli Hu12College of Information Science and Engineering, Northeastern UniversityLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesCentral Research Institute, United Imaging Healthcare GroupLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesDepartment of Nuclear Medicine, Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong UniversityDepartment of Nuclear Medicine, Ren Ji Hospital, School of Medicine, Shanghai Jiao Tong UniversityLauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of SciencesAbstract Purpose Total-body dynamic positron emission tomography (PET) imaging with total-body coverage and ultrahigh sensitivity has played an important role in accurate tracer kinetic analyses in physiology, biochemistry, and pharmacology. However, dynamic PET scans typically entail prolonged durations ( $$\:\ge\:$$ 60 minutes), potentially causing patient discomfort and resulting in artifacts in the final images. Therefore, we propose a dynamic frame prediction method for total-body PET imaging via deep learning technology to reduce the required scanning time. Methods On the basis of total-body dynamic PET data acquired from 13 subjects who received [68Ga]Ga-FAPI-04 (68Ga-FAPI) and 24 subjects who received [68Ga]Ga-PSMA-11 (68Ga-PSMA), we propose a bidirectional dynamic frame prediction network that uses the initial and final 10 min of PET imaging data (frames 1–6 and frames 25–30, respectively) as inputs. The peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were employed as evaluation metrics for an image quality assessment. Moreover, we calculated parametric images (68Ga-FAPI: $$\:{K}_{1}$$ , 68Ga-PSMA: $$\:{K}_{i}$$ ) based on the supplemented sequence data to observe the quantitative accuracy of our approach. Regions of interest (ROIs) and statistical analyses were utilized to evaluate the performance of the model. Results Both the visual and quantitative results illustrate the effectiveness of our approach. The generated dynamic PET images yielded PSNRs of 36.056 ± 0.709 dB for the 68Ga-PSMA group and 33.779 ± 0.760 dB for the 68Ga-FAPI group. Additionally, the SSIM reached 0.935 ± 0.006 for the 68Ga-FAPI group and 0.922 ± 0.009 for the 68Ga-PSMA group. By conducting a quantitative analysis on the parametric images, we obtained PSNRs of 36.155 ± 4.813 dB (68Ga-PSMA, $$\:{K}_{1}$$ ) and 43.150 ± 4.102 dB (68Ga-FAPI, $$\:{K}_{i}$$ ). The obtained SSIM values were 0.932 ± 0.041 (68Ga-PSMA) and 0.980 ± 0.011 (68Ga-FAPI). The ROI analysis conducted on our generated dynamic PET sequences also revealed that our method can accurately predict temporal voxel intensity changes, maintaining overall visual consistency with the ground truth. Conclusion In this work, we propose a bidirectional dynamic frame prediction network for total-body 68Ga-PSMA and 68Ga-FAPI PET imaging with a reduced scan duration. Visual and quantitative analyses demonstrated that our approach performed well when it was used to predict one-hour dynamic PET images. https://github.com/OPMZZZ/BDF-NET .https://doi.org/10.1186/s40658-024-00698-0Total-body dynamic PETFrame predictionImage generationDeep learning
spellingShingle Qianyi Yang
Wenbo Li
Zhenxing Huang
Zixiang Chen
Wenjie Zhao
Yunlong Gao
Xinlan Yang
Yongfeng Yang
Hairong Zheng
Dong Liang
Jianjun Liu
Ruohua Chen
Zhanli Hu
Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images
EJNMMI Physics
Total-body dynamic PET
Frame prediction
Image generation
Deep learning
title Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images
title_full Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images
title_fullStr Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images
title_full_unstemmed Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images
title_short Bidirectional dynamic frame prediction network for total-body [68Ga]Ga-PSMA-11 and [68Ga]Ga-FAPI-04 PET images
title_sort bidirectional dynamic frame prediction network for total body 68ga ga psma 11 and 68ga ga fapi 04 pet images
topic Total-body dynamic PET
Frame prediction
Image generation
Deep learning
url https://doi.org/10.1186/s40658-024-00698-0
work_keys_str_mv AT qianyiyang bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT wenboli bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT zhenxinghuang bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT zixiangchen bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT wenjiezhao bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT yunlonggao bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT xinlanyang bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT yongfengyang bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT hairongzheng bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT dongliang bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT jianjunliu bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT ruohuachen bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages
AT zhanlihu bidirectionaldynamicframepredictionnetworkfortotalbody68gagapsma11and68gagafapi04petimages