Physics-Aware Neural Operators for Direct Inversion in 3D Photoacoustic Tomography
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911497486073856 |
|---|---|
| author | Wang, Jiayun Aborahama, Yousuf Khokhar, Arya Zhang, Yang Wang, Chuwei Sastry, Karteekeya Berner, Julius Luo, Yilin Bonev, Boris Li, Zongyi Azizzadenesheli, Kamyar Wang, Lihong V. Anandkumar, Anima |
| author_facet | Wang, Jiayun Aborahama, Yousuf Khokhar, Arya Zhang, Yang Wang, Chuwei Sastry, Karteekeya Berner, Julius Luo, Yilin Bonev, Boris Li, Zongyi Azizzadenesheli, Kamyar Wang, Lihong V. Anandkumar, Anima |
| contents | Learning physics-constrained inverse operators-rather than post-processing physics-based reconstructions-is a broadly applicable strategy for problems with expensive forward models. We demonstrate this principle in three-dimensional photoacoustic computed tomography (3D PACT), where current systems demand dense transducer arrays and prolonged scans, restricting clinical translation. We introduce PANO (PACT imaging neural operator), an end-to-end physics-aware neural operator-a deep learning architecture that generalizes across input sampling densities without retraining-that directly learns the inverse mapping from raw sensor measurements to a 3D volumetric image. Unlike two-step methods that reconstruct then denoise, PANO performs direct inversion in a single pass, jointly embedding physics and data priors. It employs spherical discrete-continuous convolutions to respect hemispherical sensor geometry and Helmholtz equation constraints to ensure physical consistency. PANO reconstructs high-quality images from both simulated and real data across diverse sparse acquisition settings, achieves real-time inference and outperforms the widely-used UBP algorithm by approximately 33 percentage points in cosine similarity on simulated data and 14 percentage points on real phantom data. These results establish a pathway toward more accessible 3D PACT systems for preclinical research, and motivate future in-vivo validation for clinical translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09894 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Physics-Aware Neural Operators for Direct Inversion in 3D Photoacoustic Tomography Wang, Jiayun Aborahama, Yousuf Khokhar, Arya Zhang, Yang Wang, Chuwei Sastry, Karteekeya Berner, Julius Luo, Yilin Bonev, Boris Li, Zongyi Azizzadenesheli, Kamyar Wang, Lihong V. Anandkumar, Anima Image and Video Processing Machine Learning Learning physics-constrained inverse operators-rather than post-processing physics-based reconstructions-is a broadly applicable strategy for problems with expensive forward models. We demonstrate this principle in three-dimensional photoacoustic computed tomography (3D PACT), where current systems demand dense transducer arrays and prolonged scans, restricting clinical translation. We introduce PANO (PACT imaging neural operator), an end-to-end physics-aware neural operator-a deep learning architecture that generalizes across input sampling densities without retraining-that directly learns the inverse mapping from raw sensor measurements to a 3D volumetric image. Unlike two-step methods that reconstruct then denoise, PANO performs direct inversion in a single pass, jointly embedding physics and data priors. It employs spherical discrete-continuous convolutions to respect hemispherical sensor geometry and Helmholtz equation constraints to ensure physical consistency. PANO reconstructs high-quality images from both simulated and real data across diverse sparse acquisition settings, achieves real-time inference and outperforms the widely-used UBP algorithm by approximately 33 percentage points in cosine similarity on simulated data and 14 percentage points on real phantom data. These results establish a pathway toward more accessible 3D PACT systems for preclinical research, and motivate future in-vivo validation for clinical translation. |
| title | Physics-Aware Neural Operators for Direct Inversion in 3D Photoacoustic Tomography |
| topic | Image and Video Processing Machine Learning |
| url | https://arxiv.org/abs/2509.09894 |