深度学习辅助的光声成像综述
Photoacoustic imaging aided with deep learning: a review.
作者信息
Rajendran Praveenbalaji, Sharma Arunima, Pramanik Manojit
机构信息
School of Chemical and Biomedical Engineering, Nanyang Technological University, 62 Nanyang Drive, Singapore, 637459 Singapore.
Present Address: Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD USA.
出版信息
Biomed Eng Lett. 2021 Nov 23;12(2):155-173. doi: 10.1007/s13534-021-00210-y. eCollection 2022 May.
Abstract
Photoacoustic imaging (PAI) is an emerging hybrid imaging modality integrating the benefits of both optical and ultrasound imaging. Although PAI exhibits superior imaging capabilities, its translation into clinics is still hindered by various limitations. In recent years, deeplearning (DL), a new paradigm of machine learning, is gaining a lot of attention due to its ability to improve medical images. Likewise, DL is also widely being used in PAI to overcome some of the limitations of PAI. In this review, we provide a comprehensive overview on the various DL techniques employed in PAI along with its promising advantages.
摘要
光声成像（PAI）是一种新兴的混合成像模式，融合了光学成像和超声成像的优点。尽管PAI展现出卓越的成像能力，但其向临床应用的转化仍受到各种限制的阻碍。近年来，深度学习（DL）作为机器学习的一种新范式，因其能够改善医学图像而备受关注。同样，DL也广泛应用于PAI以克服PAI的一些局限性。在本综述中，我们全面概述了PAI中使用的各种DL技术及其显著优势。
相似文献
1
Photoacoustic imaging aided with deep learning: a review.深度学习辅助的光声成像综述
Biomed Eng Lett. 2021 Nov 23;12(2):155-173. doi: 10.1007/s13534-021-00210-y. eCollection 2022 May.
2
Deep learning in photoacoustic imaging: a review.深度学习在光声成像中的应用：综述。
J Biomed Opt. 2021 Apr;26(4). doi: 10.1117/1.JBO.26.4.040901.
3
Hybrid Neural Network for Photoacoustic Imaging Reconstruction.用于光声成像重建的混合神经网络
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:6367-6370. doi: 10.1109/EMBC.2019.8857019.
4
Deep learning for biomedical photoacoustic imaging: A review.用于生物医学光声成像的深度学习：综述
Photoacoustics. 2021 Feb 2;22:100241. doi: 10.1016/j.pacs.2021.100241. eCollection 2021 Jun.
5
Photoacoustic imaging plus X: a review.光声成像技术与 X 技术的结合：综述。
J Biomed Opt. 2024 Jan;29(Suppl 1):S11513. doi: 10.1117/1.JBO.29.S1.S11513. Epub 2023 Dec 28.
6
Recent advances toward clinical applications of photoacoustic microscopy: a review.光声显微镜临床应用的最新进展：综述。
Sci China Life Sci. 2020 Dec;63(12):1798-1812. doi: 10.1007/s11427-019-1628-7. Epub 2020 May 11.
7
Sound Out the Deep Clarity: Super-Resolution Photoacoustic Imaging at Depths.深入清晰发声：深度超分辨率光声成像
IEEE Trans Ultrason Ferroelectr Freq Control. 2024 Dec;71(12: Breaking the Resolution Barrier in Ultrasound):1801-1813. doi: 10.1109/TUFFC.2024.3451986. Epub 2025 Jan 8.
8
Review of deep learning for photoacoustic imaging.用于光声成像的深度学习综述。
Photoacoustics. 2020 Dec 29;21:100215. doi: 10.1016/j.pacs.2020.100215. eCollection 2021 Mar.
9
Photoacoustic Imaging.光声成像。
Adv Exp Med Biol. 2021;3233:147-175. doi: 10.1007/978-981-15-7627-0_8.
10
Deep Learning in Biomedical Optics.深度学习在生物医学光学中的应用。
Lasers Surg Med. 2021 Aug;53(6):748-775. doi: 10.1002/lsm.23414. Epub 2021 May 20.
引用本文的文献
1
Artifacts in photoacoustic imaging: Origins and mitigations.光声成像中的伪像：起源与抑制
Photoacoustics. 2025 Jul 5;45:100745. doi: 10.1016/j.pacs.2025.100745. eCollection 2025 Oct.
2
Temporally delayed, dual-pulse, dual-wavelength photoacoustic imaging (TD-DP-DW-PAI): advancing capabilities of a commercial light-emitting diode-based photoacoustic imaging system with a pulsed laser diode.时间延迟双脉冲双波长光声成像（TD-DP-DW-PAI）：利用脉冲激光二极管提升基于商用发光二极管的光声成像系统的性能
Biomed Opt Express. 2025 Jun 24;16(7):2945-2958. doi: 10.1364/BOE.565015. eCollection 2025 Jul 1.
3
Model-informed deep-learning photoacoustic reconstruction for low-element linear array.基于模型的深度学习低元线性阵列光声重建
Photoacoustics. 2025 May 16;44:100732. doi: 10.1016/j.pacs.2025.100732. eCollection 2025 Aug.
4
Energy estimation methods for positron emission tomography detectors composed of multiple scintillators.用于由多个闪烁体组成的正电子发射断层扫描探测器的能量估计方法。
Biomed Eng Lett. 2025 Mar 4;15(3):489-496. doi: 10.1007/s13534-025-00464-w. eCollection 2025 May.
5
High resolution photoacoustic vascular image reconstruction through the fast residual dense generative adversarial network.通过快速残差密集生成对抗网络实现高分辨率光声血管图像重建。
Photoacoustics. 2025 Apr 1;43:100720. doi: 10.1016/j.pacs.2025.100720. eCollection 2025 Jun.
6
MSD-Net: Multi-scale dense convolutional neural network for photoacoustic image reconstruction with sparse data.MSD-Net：用于稀疏数据光声图像重建的多尺度密集卷积神经网络
Photoacoustics. 2024 Dec 12;41:100679. doi: 10.1016/j.pacs.2024.100679. eCollection 2025 Feb.
7
Enhancing signal-to-noise ratio in real-time LED-based photoacoustic imaging: A comparative study of CNN-based deep learning architectures.实时基于LED的光声成像中提高信噪比：基于卷积神经网络的深度学习架构的比较研究
Photoacoustics. 2024 Nov 30;41:100674. doi: 10.1016/j.pacs.2024.100674. eCollection 2025 Feb.
8
Strategies for mitigating inter-crystal scattering effects in positron emission tomography: a comprehensive review.正电子发射断层扫描中减轻晶体间散射效应的策略：全面综述
Biomed Eng Lett. 2024 Sep 17;14(6):1243-1258. doi: 10.1007/s13534-024-00427-7. eCollection 2024 Nov.
9
Towards photoacoustic human imaging: Shining a new light on clinical diagnostics.迈向光声人体成像：为临床诊断带来新曙光。
Fundam Res. 2023 Feb 14;4(5):1314-1330. doi: 10.1016/j.fmre.2023.01.008. eCollection 2024 Sep.
10
Joint segmentation and image reconstruction with error prediction in photoacoustic imaging using deep learning.利用深度学习在光声成像中进行联合分割与图像重建并进行误差预测
Photoacoustics. 2024 Sep 11;40:100645. doi: 10.1016/j.pacs.2024.100645. eCollection 2024 Dec.
本文引用的文献
1
Deep-learning-based multi-transducer photoacoustic tomography imaging without radius calibration.基于深度学习的无需半径校准的多换能器光声断层成像。
Opt Lett. 2021 Sep 15;46(18):4510-4513. doi: 10.1364/OL.434513.
2
High-speed photoacoustic microscopy: A review dedicated on light sources.高速光声显微镜：关于光源的综述
Photoacoustics. 2021 Aug 6;24:100291. doi: 10.1016/j.pacs.2021.100291. eCollection 2021 Dec.
3
Binary photoacoustic tomography for improved vasculature imaging.二进制光声断层扫描术可改善血管成像。
J Biomed Opt. 2021 Aug;26(8). doi: 10.1117/1.JBO.26.8.086004.
4
Deep learning of image- and time-domain data enhances the visibility of structures in optoacoustic tomography.深度学习的图像和时域数据增强了光声断层扫描中结构的可视性。
Opt Lett. 2021 Jul 1;46(13):3029-3032. doi: 10.1364/OL.424571.
5
Comparing Deep Learning Frameworks for Photoacoustic Tomography Image Reconstruction.用于光声断层成像图像重建的深度学习框架比较
Photoacoustics. 2021 May 15;23:100271. doi: 10.1016/j.pacs.2021.100271. eCollection 2021 Sep.
6
Temporal and spectral unmixing of photoacoustic signals by deep learning.基于深度学习的光声信号的时频解混。
Opt Lett. 2021 Jun 1;46(11):2690-2693. doi: 10.1364/OL.426678.
7
Deep learning enabled real-time photoacoustic tomography system via single data acquisition channel.通过单数据采集通道实现深度学习的实时光声断层扫描系统。
Photoacoustics. 2021 May 5;22:100270. doi: 10.1016/j.pacs.2021.100270. eCollection 2021 Jun.
8
Deep Learning in Biomedical Optics.深度学习在生物医学光学中的应用。
Lasers Surg Med. 2021 Aug;53(6):748-775. doi: 10.1002/lsm.23414. Epub 2021 May 20.
9
Axial accuracy and signal enhancement in acoustic-resolution photoacoustic microscopy by laser jitter effect correction and pulse energy compensation.通过激光抖动效应校正和脉冲能量补偿提高声学分辨率光声显微镜的轴向精度和信号增强
Biomed Opt Express. 2021 Mar 2;12(4):1834-1845. doi: 10.1364/BOE.419564. eCollection 2021 Apr 1.
10
Deep learning: step forward to high-resolution in vivo shortwave infrared imaging.深度学习：迈向高分辨率活体短波红外成像的一大步。
J Biophotonics. 2021 Jul;14(7):e202100102. doi: 10.1002/jbio.202100102. Epub 2021 May 12.
Zotero 插件