Neural-field-based image reconstruction for bioluminescence tomography
Deep learning (DL)-based image reconstruction methods have garnered increasing interest in the last few years. Numerous studies demonstrate that DL-based reconstruction methods function admirably in optical tomographic imaging techniques, such as bioluminescence tomography (BLT). Nevertheless, nearl...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2025-01-01
|
| Series: | Journal of Innovative Optical Health Sciences |
| Subjects: | |
| Online Access: | https://www.worldscientific.com/doi/10.1142/S1793545825500026 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585081660637184 |
|---|---|
| author | Xuanxuan Zhang Xu Cao Jiulou Zhang Lin Zhang Guanglei Zhang |
| author_facet | Xuanxuan Zhang Xu Cao Jiulou Zhang Lin Zhang Guanglei Zhang |
| author_sort | Xuanxuan Zhang |
| collection | DOAJ |
| description | Deep learning (DL)-based image reconstruction methods have garnered increasing interest in the last few years. Numerous studies demonstrate that DL-based reconstruction methods function admirably in optical tomographic imaging techniques, such as bioluminescence tomography (BLT). Nevertheless, nearly every existing DL-based method utilizes an explicit neural representation for the reconstruction problem, which either consumes much memory space or requires various complicated computations. In this paper, we present a neural field (NF)-based image reconstruction scheme for BLT that uses an implicit neural representation. The proposed NF-based method establishes a transformation between the coordinate of an arbitrary spatial point and the source value of the point with a relatively light-weight multilayer perceptron, which has remarkable computational efficiency. Another simple neural network composed of two fully connected layers and a 1D convolutional layer is used to generate the neural features. Results of simulations and experiments show that the proposed NF-based method has similar performance to the photon density complement network and the two-stage network, while consuming fewer floating point operations with fewer model parameters. |
| format | Article |
| id | doaj-art-907bf8ed0f3d4007924bfeb87e8cf93b |
| institution | Kabale University |
| issn | 1793-5458 1793-7205 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Journal of Innovative Optical Health Sciences |
| spelling | doaj-art-907bf8ed0f3d4007924bfeb87e8cf93b2025-01-27T05:49:52ZengWorld Scientific PublishingJournal of Innovative Optical Health Sciences1793-54581793-72052025-01-01180110.1142/S1793545825500026Neural-field-based image reconstruction for bioluminescence tomographyXuanxuan Zhang0Xu Cao1Jiulou Zhang2Lin Zhang3Guanglei Zhang4School of Communications and Information Engineering & School of Artificial Intelligence, Xi’an University of Posts and Telecommunications, Xi’an, Shaanxi 710121, P. R. ChinaEngineering Research Center of Molecular and Neuro Imaging of the Ministry of Education & School of Life Science and Technology, Xidian University, Xi’an, Shaanxi 710071, P. R. ChinaDepartment of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu 210029, P. R. ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan, Shandong 250014, P. R. ChinaSchool of Biological Science and Medical Engineering, Beihang University, Beijing 100191, P. R. ChinaDeep learning (DL)-based image reconstruction methods have garnered increasing interest in the last few years. Numerous studies demonstrate that DL-based reconstruction methods function admirably in optical tomographic imaging techniques, such as bioluminescence tomography (BLT). Nevertheless, nearly every existing DL-based method utilizes an explicit neural representation for the reconstruction problem, which either consumes much memory space or requires various complicated computations. In this paper, we present a neural field (NF)-based image reconstruction scheme for BLT that uses an implicit neural representation. The proposed NF-based method establishes a transformation between the coordinate of an arbitrary spatial point and the source value of the point with a relatively light-weight multilayer perceptron, which has remarkable computational efficiency. Another simple neural network composed of two fully connected layers and a 1D convolutional layer is used to generate the neural features. Results of simulations and experiments show that the proposed NF-based method has similar performance to the photon density complement network and the two-stage network, while consuming fewer floating point operations with fewer model parameters.https://www.worldscientific.com/doi/10.1142/S1793545825500026Bioluminescence tomographyimage reconstructionneural field |
| spellingShingle | Xuanxuan Zhang Xu Cao Jiulou Zhang Lin Zhang Guanglei Zhang Neural-field-based image reconstruction for bioluminescence tomography Journal of Innovative Optical Health Sciences Bioluminescence tomography image reconstruction neural field |
| title | Neural-field-based image reconstruction for bioluminescence tomography |
| title_full | Neural-field-based image reconstruction for bioluminescence tomography |
| title_fullStr | Neural-field-based image reconstruction for bioluminescence tomography |
| title_full_unstemmed | Neural-field-based image reconstruction for bioluminescence tomography |
| title_short | Neural-field-based image reconstruction for bioluminescence tomography |
| title_sort | neural field based image reconstruction for bioluminescence tomography |
| topic | Bioluminescence tomography image reconstruction neural field |
| url | https://www.worldscientific.com/doi/10.1142/S1793545825500026 |
| work_keys_str_mv | AT xuanxuanzhang neuralfieldbasedimagereconstructionforbioluminescencetomography AT xucao neuralfieldbasedimagereconstructionforbioluminescencetomography AT jiulouzhang neuralfieldbasedimagereconstructionforbioluminescencetomography AT linzhang neuralfieldbasedimagereconstructionforbioluminescencetomography AT guangleizhang neuralfieldbasedimagereconstructionforbioluminescencetomography |