Denoising of pre-beamformed photoacoustic data using generative adversarial networks

Refaee, Amir; Kelly, Corey J.; Moradi, Hamid; Salcudean, Septimiu E.

doi:10.1364/boe.431997

Cited by 10 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work demonstrates that the BFP-GAN model is effective in denoising PA data. [9] Unlike traditional GAN models, the Pix2Pix GAN [10] model requires paired data for training. Specifically, the discriminator is trained on both <𝑥, 𝑦 and < 𝑥, 𝐺 𝑥 pairs, where 𝐺 𝑥 represents the output image generated by the generator from the input image 𝑥 The objective of training the Pix2Pix GAN model is to minimize the following loss function:…”

Section: Framework Of Bfp-gan Modelmentioning

confidence: 99%

Enhancing photoacoustic imaging with BFP-GAN

huang,

Liu,

Guo

2024

International Academic Conference on Optics and Photonics (IACOP 2023)

View full text Add to dashboard Cite

This study introduces Binary Fourier Perception Generative Adversarial Network (BFP-GAN), a tailored approach for improved photoacoustic image generation in data-sparse environments. By combining GAN and Fourier decay perception techniques, the method markedly enhances image quality. Experimental validation using PAM and PAT datasets demonstrates its effectiveness in reducing artifacts and improving fidelity with limited data. BFP-GAN holds significant promise for diverse clinical applications, representing a major advancement in photoacoustic imaging technology.

show abstract

Section: Framework Of Bfp-gan Modelmentioning

confidence: 99%

Enhancing photoacoustic imaging with BFP-GAN

huang,

Liu,

Guo

2024

International Academic Conference on Optics and Photonics (IACOP 2023)

View full text Add to dashboard Cite

show abstract

“…The Pix2Pix GAN was used for image reconstruction, as it has shown promising results in PA image denoising and reconstruction 9,10 . This model is a general-purpose neural network that can be trained to solve image-to-image translation problems 11 .…”

Section: Pix2pix Ganmentioning

confidence: 99%

Multiple photoacoustic sources localization using deep learning

de Jong,

Moradi,

Vousten

et al. 2024

Medical Imaging 2024: Ultrasonic Imaging and Tomography

View full text Add to dashboard Cite

Photoacoustic imaging (PAI) has emerged as a promising technique for various image guidance procedures. While convolutional neural networks (CNNs) trained on simulated radiofrequency (RF) data have been employed for point source reconstruction, their performance on real data remains a challenge. This paper addresses this limitation by introducing a novel deep learning-based method that utilizes a limited amount of experimental laser-diode-based data for the reconstruction of multiple point sources. The proposed approach employs a dual generative adversarial network (Dual-GAN) trained on experimental RF data from a combination of point source images. The Dual-GAN exhibits superior performance compared to the conventional delay-and-sum (DAS) method, demonstrating enhanced image contrast and a reduced full width at half maximum (FWHM). Notably, the axial and lateral localization errors of the Dual-GAN predictions surpass previous studies, measuring 0.028 ± 0.018 mm and 0.087 ± 0.096 mm, respectively. Additionally, the model demonstrates generalization capability by successfully reconstructing multiple point sources imaged using a different Nd:YAG laser system. This innovative method marks a significant advancement, offering improved accuracy and versatility in PAI applications involving multiple point sources.

show abstract

“…DL methods were also employed for data visualization, reconstruction, and improve/enhance OAI 40 – 52 Recently, a few DL methods were proposed for fluence compensation in OAI, 42 , 44 – 46 , 53 , 54 but those studies considered simple phantoms such as point/dot, discs, line phantoms, and circle phantom 44 , 46 , 53 . Very less emphasis has been placed on evaluating the performance of DL models for fluence compensation on ex-vivo 54 or in-vivo 44 , 54 data.…”

Section: Introductionmentioning

confidence: 99%

Deep learning methods hold promise for light fluence compensation in three-dimensional optoacoustic imaging

et al. 2022

View full text Add to dashboard Cite

. Significance: Quantitative optoacoustic imaging (QOAI) continues to be a challenge due to the influence of nonlinear optical fluence distribution, which distorts the optoacoustic image representation. Nonlinear optical fluence correction in OA imaging is highly ill-posed, leading to the inaccurate recovery of optical absorption maps. This work aims to recover the optical absorption maps using deep learning (DL) approach by correcting for the fluence effect. Aim: Different DL models were compared and investigated to enable optical absorption coefficient recovery at a particular wavelength in a nonhomogeneous foreground and background medium. Approach: Data-driven models were trained with two-dimensional (2D) Blood vessel and three-dimensional (3D) numerical breast phantom with highly heterogeneous/realistic structures to correct for the nonlinear optical fluence distribution. The trained DL models such as U-Net, Fully Dense (FD) U-Net, Y-Net, FD Y-Net, Deep residual U-Net (Deep ResU-Net), and generative adversarial network (GAN) were tested to evaluate the performance of optical absorption coefficient recovery (or fluence compensation) with in-silico and in-vivo datasets. Results: The results indicated that FD U-Net-based deconvolution improves by about 10% over reconstructed optoacoustic images in terms of peak-signal-to-noise ratio. Further, it was observed that DL models can indeed highlight deep-seated structures with higher contrast due to fluence compensation. Importantly, the DL models were found to be about 17 times faster than solving diffusion equation for fluence correction. Conclusions: The DL methods were able to compensate for nonlinear optical fluence distribution more effectively and improve the optoacoustic image quality.

show abstract

Denoising of pre-beamformed photoacoustic data using generative adversarial networks

Cited by 10 publications

References 32 publications

Enhancing photoacoustic imaging with BFP-GAN

Enhancing photoacoustic imaging with BFP-GAN

Multiple photoacoustic sources localization using deep learning

Deep learning methods hold promise for light fluence compensation in three-dimensional optoacoustic imaging

Contact Info

Product

Resources

About