Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography
Real-time applications in three-dimensional photoacoustic tomography from planar sensors rely on fast reconstruction algorithms that assume the speed of sound (SoS) in the tissue is homogeneous. Moreover, the reconstruction quality depends on the correct choice for the constant SoS. In this study, w...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Photoacoustics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213597924000144 |
| _version_ | 1797248330672111616 |
|---|---|
| author | Jenni Poimala Ben Cox Andreas Hauptmann |
| author_facet | Jenni Poimala Ben Cox Andreas Hauptmann |
| author_sort | Jenni Poimala |
| collection | DOAJ |
| description | Real-time applications in three-dimensional photoacoustic tomography from planar sensors rely on fast reconstruction algorithms that assume the speed of sound (SoS) in the tissue is homogeneous. Moreover, the reconstruction quality depends on the correct choice for the constant SoS. In this study, we discuss the possibility of ameliorating the problem of unknown or heterogeneous SoS distributions by using learned reconstruction methods. This can be done by modelling the uncertainties in the training data. In addition, a correction term can be included in the learned reconstruction method. We investigate the influence of both and while a learned correction component can improve reconstruction quality further, we show that a careful choice of uncertainties in the training data is the primary factor to overcome unknown SoS. We support our findings with simulated and in vivo measurements in 3D. |
| first_indexed | 2024-03-07T22:00:56Z |
| format | Article |
| id | doaj.art-35e3280873b949c2a7d2a91304c1286e |
| institution | Directory Open Access Journal |
| issn | 2213-5979 |
| language | English |
| last_indexed | 2024-04-24T20:12:53Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Photoacoustics |
| spelling | doaj.art-35e3280873b949c2a7d2a91304c1286e2024-03-23T06:24:11ZengElsevierPhotoacoustics2213-59792024-06-0137100597Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomographyJenni Poimala0Ben Cox1Andreas Hauptmann2Research Unit of Mathematical Sciences, University of Oulu, Finland; Corresponding author.Department of Medical Physics and Biomedical Engineering, University College London, UKResearch Unit of Mathematical Sciences, University of Oulu, Finland; Department of Computer Science, University College London, UKReal-time applications in three-dimensional photoacoustic tomography from planar sensors rely on fast reconstruction algorithms that assume the speed of sound (SoS) in the tissue is homogeneous. Moreover, the reconstruction quality depends on the correct choice for the constant SoS. In this study, we discuss the possibility of ameliorating the problem of unknown or heterogeneous SoS distributions by using learned reconstruction methods. This can be done by modelling the uncertainties in the training data. In addition, a correction term can be included in the learned reconstruction method. We investigate the influence of both and while a learned correction component can improve reconstruction quality further, we show that a careful choice of uncertainties in the training data is the primary factor to overcome unknown SoS. We support our findings with simulated and in vivo measurements in 3D.http://www.sciencedirect.com/science/article/pii/S2213597924000144Photoacoustic tomographyConvolutional neural networksComplex valued neural networksImage reconstructionSpeed of sound compensation |
| spellingShingle | Jenni Poimala Ben Cox Andreas Hauptmann Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography Photoacoustics Photoacoustic tomography Convolutional neural networks Complex valued neural networks Image reconstruction Speed of sound compensation |
| title | Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography |
| title_full | Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography |
| title_fullStr | Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography |
| title_full_unstemmed | Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography |
| title_short | Compensating unknown speed of sound in learned fast 3D limited-view photoacoustic tomography |
| title_sort | compensating unknown speed of sound in learned fast 3d limited view photoacoustic tomography |
| topic | Photoacoustic tomography Convolutional neural networks Complex valued neural networks Image reconstruction Speed of sound compensation |
| url | http://www.sciencedirect.com/science/article/pii/S2213597924000144 |
| work_keys_str_mv | AT jennipoimala compensatingunknownspeedofsoundinlearnedfast3dlimitedviewphotoacoustictomography AT bencox compensatingunknownspeedofsoundinlearnedfast3dlimitedviewphotoacoustictomography AT andreashauptmann compensatingunknownspeedofsoundinlearnedfast3dlimitedviewphotoacoustictomography |