Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction
Photoacoustic imaging (PAI) is a noninvasive emerging imaging method based on the photoacoustic effect, which provides necessary assistance for medical diagnosis. It has the characteristics of large imaging depth and high contrast. However, limited by the equipment cost and reconstruction time requi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2024-05-01
|
| Series: | Journal of Innovative Optical Health Sciences |
| Subjects: | |
| Online Access: | https://www.worldscientific.com/doi/10.1142/S1793545823500281 |
| _version_ | 1797216859960901632 |
|---|---|
| author | Lingyu Ma Zezheng Qin Yiming Ma Mingjian Sun |
| author_facet | Lingyu Ma Zezheng Qin Yiming Ma Mingjian Sun |
| author_sort | Lingyu Ma |
| collection | DOAJ |
| description | Photoacoustic imaging (PAI) is a noninvasive emerging imaging method based on the photoacoustic effect, which provides necessary assistance for medical diagnosis. It has the characteristics of large imaging depth and high contrast. However, limited by the equipment cost and reconstruction time requirements, the existing PAI systems distributed with annular array transducers are difficult to take into account both the image quality and the imaging speed. In this paper, a triple-path feature transform network (TFT-Net) for ring-array photoacoustic tomography is proposed to enhance the imaging quality from limited-view and sparse measurement data. Specifically, the network combines the raw photoacoustic pressure signals and conventional linear reconstruction images as input data, and takes the photoacoustic physical model as a prior information to guide the reconstruction process. In addition, to enhance the ability of extracting signal features, the residual block and squeeze and excitation block are introduced into the TFT-Net. For further efficient reconstruction, the final output of photoacoustic signals uses ‘filter-then-upsample’ operation with a pixel-shuffle multiplexer and a max out module. Experiment results on simulated and in-vivo data demonstrate that the constructed TFT-Net can restore the target boundary clearly, reduce background noise, and realize fast and high-quality photoacoustic image reconstruction of limited view with sparse sampling. |
| first_indexed | 2024-04-24T11:52:40Z |
| format | Article |
| id | doaj.art-ca844e8053e64a23a67a3364c75534be |
| institution | Directory Open Access Journal |
| issn | 1793-5458 1793-7205 |
| language | English |
| last_indexed | 2024-04-24T11:52:40Z |
| publishDate | 2024-05-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Journal of Innovative Optical Health Sciences |
| spelling | doaj.art-ca844e8053e64a23a67a3364c75534be2024-04-09T07:13:16ZengWorld Scientific PublishingJournal of Innovative Optical Health Sciences1793-54581793-72052024-05-01170310.1142/S1793545823500281Triple-path feature transform network for ring-array photoacoustic tomography image reconstructionLingyu Ma0Zezheng Qin1Yiming Ma2Mingjian Sun3School of Astronautics, Harbin Institute of Technology, Harbin, Heilongjiang 150000, P. R. ChinaSchool of Astronautics, Harbin Institute of Technology, Harbin, Heilongjiang 150000, P. R. ChinaSchool of Astronautics, Harbin Institute of Technology, Harbin, Heilongjiang 150000, P. R. ChinaSchool of Astronautics, Harbin Institute of Technology, Harbin, Heilongjiang 150000, P. R. ChinaPhotoacoustic imaging (PAI) is a noninvasive emerging imaging method based on the photoacoustic effect, which provides necessary assistance for medical diagnosis. It has the characteristics of large imaging depth and high contrast. However, limited by the equipment cost and reconstruction time requirements, the existing PAI systems distributed with annular array transducers are difficult to take into account both the image quality and the imaging speed. In this paper, a triple-path feature transform network (TFT-Net) for ring-array photoacoustic tomography is proposed to enhance the imaging quality from limited-view and sparse measurement data. Specifically, the network combines the raw photoacoustic pressure signals and conventional linear reconstruction images as input data, and takes the photoacoustic physical model as a prior information to guide the reconstruction process. In addition, to enhance the ability of extracting signal features, the residual block and squeeze and excitation block are introduced into the TFT-Net. For further efficient reconstruction, the final output of photoacoustic signals uses ‘filter-then-upsample’ operation with a pixel-shuffle multiplexer and a max out module. Experiment results on simulated and in-vivo data demonstrate that the constructed TFT-Net can restore the target boundary clearly, reduce background noise, and realize fast and high-quality photoacoustic image reconstruction of limited view with sparse sampling.https://www.worldscientific.com/doi/10.1142/S1793545823500281Deep learningfeature transformationimage reconstructionlimited-view measurementphotoacoustic tomography |
| spellingShingle | Lingyu Ma Zezheng Qin Yiming Ma Mingjian Sun Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction Journal of Innovative Optical Health Sciences Deep learning feature transformation image reconstruction limited-view measurement photoacoustic tomography |
| title | Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction |
| title_full | Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction |
| title_fullStr | Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction |
| title_full_unstemmed | Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction |
| title_short | Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction |
| title_sort | triple path feature transform network for ring array photoacoustic tomography image reconstruction |
| topic | Deep learning feature transformation image reconstruction limited-view measurement photoacoustic tomography |
| url | https://www.worldscientific.com/doi/10.1142/S1793545823500281 |
| work_keys_str_mv | AT lingyuma triplepathfeaturetransformnetworkforringarrayphotoacoustictomographyimagereconstruction AT zezhengqin triplepathfeaturetransformnetworkforringarrayphotoacoustictomographyimagereconstruction AT yimingma triplepathfeaturetransformnetworkforringarrayphotoacoustictomographyimagereconstruction AT mingjiansun triplepathfeaturetransformnetworkforringarrayphotoacoustictomographyimagereconstruction |