Model-informed deep-learning photoacoustic reconstruction for low-element linear array
Photoacoustic tomography (PAT), widely applied using linear array ultrasound transducers for clinical and preclinical imaging, faces significant challenges due to sparse sensor arrangements and limited sensor pitch. These factors often compromise image quality, particularly in devices designed to ha...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-08-01
|
| Series: | Photoacoustics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213597925000552 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839650392123637760 |
|---|---|
| author | Souradip Paul S. Alex Lee Shensheng Zhao Yun-Sheng Chen |
| author_facet | Souradip Paul S. Alex Lee Shensheng Zhao Yun-Sheng Chen |
| author_sort | Souradip Paul |
| collection | DOAJ |
| description | Photoacoustic tomography (PAT), widely applied using linear array ultrasound transducers for clinical and preclinical imaging, faces significant challenges due to sparse sensor arrangements and limited sensor pitch. These factors often compromise image quality, particularly in devices designed to have fewer sensors to reduce complexity and power consumption, such as wearable systems. Conventional reconstruction methods, including delay-and-sum and iterative model-based techniques, either lack accuracy or are computationally intensive. Recent advancements in deep learning offer promising improvements. In particular, model-based deep learning combines physics-informed priors with neural networks to enhance reconstruction quality and reduce computational demands. However, model matrix inversion during adjoint transformations presents computational challenges in model-based deep learning. To address the challenges, we introduce a simplified, efficient GE-CNN framework specifically tailored for linear array transducers. Our lightweight GE-CNN architecture significantly reduces computational demand, achieving a 4-fold reduction in model matrix size (2.09 GB for 32 elements vs. 8.38 GB for 128 elements) and accelerating processing by approximately 46.3 %, reducing the processing time from 7.88 seconds to 4.23 seconds. We rigorously evaluated this approach using synthetic models, experimental phantoms, and in-vivo rat liver imaging, highlighting the improved reconstruction performance with minimal hardware. |
| format | Article |
| id | doaj-art-ab0b9515ac3d4928b4e02a59adb4d895 |
| institution | Matheson Library |
| issn | 2213-5979 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Photoacoustics |
| spelling | doaj-art-ab0b9515ac3d4928b4e02a59adb4d8952025-06-27T05:50:22ZengElsevierPhotoacoustics2213-59792025-08-0144100732Model-informed deep-learning photoacoustic reconstruction for low-element linear arraySouradip Paul0S. Alex Lee1Shensheng Zhao2Yun-Sheng Chen3Beckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign, Urbana, IL, USA; Nick Holonyak Micro and Nanotechnology Laboratory, University of Illinois Urbana-Champaign, Urbana, IL, USA; Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USABeckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign, Urbana, IL, USA; Nick Holonyak Micro and Nanotechnology Laboratory, University of Illinois Urbana-Champaign, Urbana, IL, USA; Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USABeckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign, Urbana, IL, USA; Nick Holonyak Micro and Nanotechnology Laboratory, University of Illinois Urbana-Champaign, Urbana, IL, USA; Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USABeckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign, Urbana, IL, USA; Nick Holonyak Micro and Nanotechnology Laboratory, University of Illinois Urbana-Champaign, Urbana, IL, USA; Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA; Department of Bioengineering, University of Illinois Urbana-Champaign, Urbana, IL, USA; Department of Biomedical and Translational Sciences, Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, IL, USA; Cancer Center at Illinois, University of Illinois Urbana-Champaign, Urbana, IL, USA; Corresponding author at: Beckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign, Urbana, IL, USA.Photoacoustic tomography (PAT), widely applied using linear array ultrasound transducers for clinical and preclinical imaging, faces significant challenges due to sparse sensor arrangements and limited sensor pitch. These factors often compromise image quality, particularly in devices designed to have fewer sensors to reduce complexity and power consumption, such as wearable systems. Conventional reconstruction methods, including delay-and-sum and iterative model-based techniques, either lack accuracy or are computationally intensive. Recent advancements in deep learning offer promising improvements. In particular, model-based deep learning combines physics-informed priors with neural networks to enhance reconstruction quality and reduce computational demands. However, model matrix inversion during adjoint transformations presents computational challenges in model-based deep learning. To address the challenges, we introduce a simplified, efficient GE-CNN framework specifically tailored for linear array transducers. Our lightweight GE-CNN architecture significantly reduces computational demand, achieving a 4-fold reduction in model matrix size (2.09 GB for 32 elements vs. 8.38 GB for 128 elements) and accelerating processing by approximately 46.3 %, reducing the processing time from 7.88 seconds to 4.23 seconds. We rigorously evaluated this approach using synthetic models, experimental phantoms, and in-vivo rat liver imaging, highlighting the improved reconstruction performance with minimal hardware.http://www.sciencedirect.com/science/article/pii/S2213597925000552Photoacoustic imagingPATBeamformingReconstruction |
| spellingShingle | Souradip Paul S. Alex Lee Shensheng Zhao Yun-Sheng Chen Model-informed deep-learning photoacoustic reconstruction for low-element linear array Photoacoustics Photoacoustic imaging PAT Beamforming Reconstruction |
| title | Model-informed deep-learning photoacoustic reconstruction for low-element linear array |
| title_full | Model-informed deep-learning photoacoustic reconstruction for low-element linear array |
| title_fullStr | Model-informed deep-learning photoacoustic reconstruction for low-element linear array |
| title_full_unstemmed | Model-informed deep-learning photoacoustic reconstruction for low-element linear array |
| title_short | Model-informed deep-learning photoacoustic reconstruction for low-element linear array |
| title_sort | model informed deep learning photoacoustic reconstruction for low element linear array |
| topic | Photoacoustic imaging PAT Beamforming Reconstruction |
| url | http://www.sciencedirect.com/science/article/pii/S2213597925000552 |
| work_keys_str_mv | AT souradippaul modelinformeddeeplearningphotoacousticreconstructionforlowelementlineararray AT salexlee modelinformeddeeplearningphotoacousticreconstructionforlowelementlineararray AT shenshengzhao modelinformeddeeplearningphotoacousticreconstructionforlowelementlineararray AT yunshengchen modelinformeddeeplearningphotoacousticreconstructionforlowelementlineararray |