.png){kind=icon}
.png){kind=icon}
Return
Efficient denoising in LED-based optoacoustic tomography with squeeze-and-excitation deep convolutional networks
.png){kind=icon}
PRE
AI
X
L
D
K
R
DOI：10.1117/1.JBO.31.4.046003.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Significance: Low-cost optoacoustic imaging based on light-emitting diodes (LEDs) offers an affordable alternative to traditional laser-based systems, potentially broadening the reach of this technology into resource-limited settings. However, LEDs are only able to excite very weak optoacoustic responses, which leads to prominent noise artifacts in the reconstructed images. Aim: We aim to mitigate noise-related artifacts in LED-based optoacoustic tomography and thereby enhance the image quality and usability of these low-cost systems. Approach: We propose a squeeze-and-excitation U-Net-based model (SE-UNet) for noise artifact reduction. The network incorporates a VGG19 convolutional neural network mid-layer feature extractor as a loss evaluation module. It is trained on noisy data paired with high-quality reference images generated using a conventional solid-state pulsed laser source. Results: Our model achieves consistent improvements on no-reference image-quality metrics (NIQE and BRISQUE) and in the contrast-to-noise ratio, effectively reducing noise artifacts while preserving image structure and details. In addition, it exhibits a rapid processing time of similar to 3ms per 480 & times;480pixel image on a GTX 2070 GPU, utilizing 627 MB of memory. Conclusions: These results highlight the potential of the proposed SE-UNet model for optimizing the performance of LED-based optoacoustic imaging systems, offering both high efficiency and improved image quality.
Keywords:
optoacoustic imaging
photoacoustics
deep learning
artifacts
denoising
light-emitting diode
Journal
IF:
2.9
Papers:
7.4K
Citations:
1.4W
Organization
Cited Papers