Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration
As a non-invasive hybrid biomedical imaging technology, photoacoustic tomography combines high contrast of optical imaging and high penetration of acoustic imaging. However, the conventional standard reconstruction under sparse view could result in low-quality image in photoacoustic tomography. Here...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Photoacoustics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213597923001118 |
| _version_ | 1797643601947131904 |
|---|---|
| author | Xianlin Song Guijun Wang Wenhua Zhong Kangjun Guo Zilong Li Xuan Liu Jiaqing Dong Qiegen Liu |
| author_facet | Xianlin Song Guijun Wang Wenhua Zhong Kangjun Guo Zilong Li Xuan Liu Jiaqing Dong Qiegen Liu |
| author_sort | Xianlin Song |
| collection | DOAJ |
| description | As a non-invasive hybrid biomedical imaging technology, photoacoustic tomography combines high contrast of optical imaging and high penetration of acoustic imaging. However, the conventional standard reconstruction under sparse view could result in low-quality image in photoacoustic tomography. Here, a novel model-based sparse reconstruction method for photoacoustic tomography via diffusion model was proposed. A score-based diffusion model is designed for learning the prior information of the data distribution. The learned prior information is utilized as a constraint for the data consistency term of an optimization problem based on the least-square method in the model-based iterative reconstruction, aiming to achieve the optimal solution. Blood vessels simulation data and the animal in vivo experimental data were used to evaluate the performance of the proposed method. The results demonstrate that the proposed method achieves higher-quality sparse reconstruction compared with conventional reconstruction methods and U-Net. In particular, under the extreme sparse projection (e.g., 32 projections), the proposed method achieves an improvement of ∼ 260 % in structural similarity and ∼ 30 % in peak signal-to-noise ratio for in vivo data, compared with the conventional delay-and-sum method. This method has the potential to reduce the acquisition time and cost of photoacoustic tomography, which will further expand the application range. |
| first_indexed | 2024-03-11T14:17:16Z |
| format | Article |
| id | doaj.art-710ae618ed974f048b14a44103560bb7 |
| institution | Directory Open Access Journal |
| issn | 2213-5979 |
| language | English |
| last_indexed | 2024-03-11T14:17:16Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Photoacoustics |
| spelling | doaj.art-710ae618ed974f048b14a44103560bb72023-11-01T04:47:11ZengElsevierPhotoacoustics2213-59792023-10-0133100558Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iterationXianlin Song0Guijun Wang1Wenhua Zhong2Kangjun Guo3Zilong Li4Xuan Liu5Jiaqing Dong6Qiegen Liu7School of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaCorresponding author.; School of Information Engineering, Nanchang University, Nanchang 330031, ChinaAs a non-invasive hybrid biomedical imaging technology, photoacoustic tomography combines high contrast of optical imaging and high penetration of acoustic imaging. However, the conventional standard reconstruction under sparse view could result in low-quality image in photoacoustic tomography. Here, a novel model-based sparse reconstruction method for photoacoustic tomography via diffusion model was proposed. A score-based diffusion model is designed for learning the prior information of the data distribution. The learned prior information is utilized as a constraint for the data consistency term of an optimization problem based on the least-square method in the model-based iterative reconstruction, aiming to achieve the optimal solution. Blood vessels simulation data and the animal in vivo experimental data were used to evaluate the performance of the proposed method. The results demonstrate that the proposed method achieves higher-quality sparse reconstruction compared with conventional reconstruction methods and U-Net. In particular, under the extreme sparse projection (e.g., 32 projections), the proposed method achieves an improvement of ∼ 260 % in structural similarity and ∼ 30 % in peak signal-to-noise ratio for in vivo data, compared with the conventional delay-and-sum method. This method has the potential to reduce the acquisition time and cost of photoacoustic tomography, which will further expand the application range.http://www.sciencedirect.com/science/article/pii/S2213597923001118Photoacoustic tomographySparse reconstructionDiffusion model |
| spellingShingle | Xianlin Song Guijun Wang Wenhua Zhong Kangjun Guo Zilong Li Xuan Liu Jiaqing Dong Qiegen Liu Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration Photoacoustics Photoacoustic tomography Sparse reconstruction Diffusion model |
| title | Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration |
| title_full | Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration |
| title_fullStr | Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration |
| title_full_unstemmed | Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration |
| title_short | Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration |
| title_sort | sparse view reconstruction for photoacoustic tomography combining diffusion model with model based iteration |
| topic | Photoacoustic tomography Sparse reconstruction Diffusion model |
| url | http://www.sciencedirect.com/science/article/pii/S2213597923001118 |
| work_keys_str_mv | AT xianlinsong sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration AT guijunwang sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration AT wenhuazhong sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration AT kangjunguo sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration AT zilongli sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration AT xuanliu sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration AT jiaqingdong sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration AT qiegenliu sparseviewreconstructionforphotoacoustictomographycombiningdiffusionmodelwithmodelbasediteration |