Lightweight denoising speckle contrast image GAN for real-time denoising of laser speckle imaging of blood flow

用于实时去噪激光散斑成像血流图像的轻量级去噪散斑对比图像生成对抗网络(GAN)

阅读:1

Abstract

To tackle real-time denoising of noisy laser speckle blood flow images, a novel lightweight denoising speckle contrast image generative adversarial network (LDSCI-GAN) is proposed. In the framework, a lightweight denoiser removes noise from the original image, and a discriminator compares the denoised result with the reference one, enabling efficient learning and optimization of the denoising process. With a multi-scale loss function in the log-transformed domain, the training process significantly improves accuracy and denoising by using only five frames of raw speckle images while well-preserving the overall pixel distribution and vascular contours. Animal and phantom experimental results indicate that the LDSCI-GAN can eliminate vascular artifacts while retaining the accuracy of relative blood flow velocity. In terms of peak signal-to-noise ratio (PSNR), mean structural similarity index (MSSIM), and Pearson correlation coefficient (R), the LDSCI-GAN outperforms other deep-learning methods by 3.07 dB, 0.10 (p < 0.001), and 0.09 (p = 0.023), respectively. It has been successfully applied to the real-time monitoring of laser-induced thrombosis. Through conducting tests on the denoising performance of blood flow images of a moving subject, our proposed method achieved enhancements of 23.6% in PSNR, 30% in MSSIM, and 6.5% in the metric R, respectively, when compared to DRSNet. This means that the LDSCI-GAN also shows possible application in handheld devices, offering a potent tool for investigating blood flow and thrombosis dynamics more efficiently and conveniently.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。