Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equation

Deep learning (DL) shows promise in estimating the absorption coefficient distribution of biological tissue in quantitative photoacoustic tomography (QPAT) imaging, but its application is limited by a lack of ground truth for supervised network training. To address this issue, we propose a DL-based...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaoyong Liang, Zongxin Mo, Shuangyang Zhang, Long Chen, Danni Wang, Chaobin Hu, Li Qi
Format: Article
Language:English
Published: Elsevier 2025-04-01
Series:Photoacoustics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2213597925000035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850240057352388608
author Zhaoyong Liang
Zongxin Mo
Shuangyang Zhang
Long Chen
Danni Wang
Chaobin Hu
Li Qi
author_facet Zhaoyong Liang
Zongxin Mo
Shuangyang Zhang
Long Chen
Danni Wang
Chaobin Hu
Li Qi
author_sort Zhaoyong Liang
collection DOAJ
description Deep learning (DL) shows promise in estimating the absorption coefficient distribution of biological tissue in quantitative photoacoustic tomography (QPAT) imaging, but its application is limited by a lack of ground truth for supervised network training. To address this issue, we propose a DL-based light fluence correction method that only uses the original PAT images for network training. Our self-supervised QPAT network model, which we termed SQPA-Net, introduces light fluence estimation based on diffusion equation to the loss function, and thus guides the model to learn an implicit representation of photoacoustic light transport within tissue. Simulation and small animal imaging experiments demonstrate the effectiveness and efficiency of our method. Compared to current DL-based methods and traditional iterative correction method, the proposed SQPA-Net achieves better light fluence correction results and significantly reduces the processing time.
format Article
id doaj-art-17f2aa9afd824e76b0717c41cd0ddcde
institution OA Journals
issn 2213-5979
language English
publishDate 2025-04-01
publisher Elsevier
record_format Article
series Photoacoustics
spelling doaj-art-17f2aa9afd824e76b0717c41cd0ddcde2025-08-20T02:00:59ZengElsevierPhotoacoustics2213-59792025-04-014210068410.1016/j.pacs.2025.100684Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equationZhaoyong Liang0Zongxin Mo1Shuangyang Zhang2Long Chen3Danni Wang4Chaobin Hu5Li Qi6School of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, ChinaSchool of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, ChinaSchool of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, ChinaSchool of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, ChinaSchool of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, ChinaSchool of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, ChinaSchool of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China; Corresponding author at: School of Biomedical Engineering, Southern Medical University, 1023 Shatai Rd., Baiyun District, Guangzhou, Guangdong 510515, China.Deep learning (DL) shows promise in estimating the absorption coefficient distribution of biological tissue in quantitative photoacoustic tomography (QPAT) imaging, but its application is limited by a lack of ground truth for supervised network training. To address this issue, we propose a DL-based light fluence correction method that only uses the original PAT images for network training. Our self-supervised QPAT network model, which we termed SQPA-Net, introduces light fluence estimation based on diffusion equation to the loss function, and thus guides the model to learn an implicit representation of photoacoustic light transport within tissue. Simulation and small animal imaging experiments demonstrate the effectiveness and efficiency of our method. Compared to current DL-based methods and traditional iterative correction method, the proposed SQPA-Net achieves better light fluence correction results and significantly reduces the processing time.http://www.sciencedirect.com/science/article/pii/S2213597925000035Quantitative photoacoustic tomographyLight fluence correctionSelf-supervised learningAbsorption coefficient estimation
spellingShingle Zhaoyong Liang
Zongxin Mo
Shuangyang Zhang
Long Chen
Danni Wang
Chaobin Hu
Li Qi
Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equation
Photoacoustics
Quantitative photoacoustic tomography
Light fluence correction
Self-supervised learning
Absorption coefficient estimation
title Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equation
title_full Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equation
title_fullStr Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equation
title_full_unstemmed Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equation
title_short Self-supervised light fluence correction network for photoacoustic tomography based on diffusion equation
title_sort self supervised light fluence correction network for photoacoustic tomography based on diffusion equation
topic Quantitative photoacoustic tomography
Light fluence correction
Self-supervised learning
Absorption coefficient estimation
url http://www.sciencedirect.com/science/article/pii/S2213597925000035
work_keys_str_mv AT zhaoyongliang selfsupervisedlightfluencecorrectionnetworkforphotoacoustictomographybasedondiffusionequation
AT zongxinmo selfsupervisedlightfluencecorrectionnetworkforphotoacoustictomographybasedondiffusionequation
AT shuangyangzhang selfsupervisedlightfluencecorrectionnetworkforphotoacoustictomographybasedondiffusionequation
AT longchen selfsupervisedlightfluencecorrectionnetworkforphotoacoustictomographybasedondiffusionequation
AT danniwang selfsupervisedlightfluencecorrectionnetworkforphotoacoustictomographybasedondiffusionequation
AT chaobinhu selfsupervisedlightfluencecorrectionnetworkforphotoacoustictomographybasedondiffusionequation
AT liqi selfsupervisedlightfluencecorrectionnetworkforphotoacoustictomographybasedondiffusionequation