Deep-learning-based 3D blood flow reconstruction in transmissive laser speckle imaging

Transmissive laser speckle imaging (LSI) is useful for mon-itoring large field-of-view (FOV) blood flow in thick tissues. However, after longer transmissions, the contrast of the transmitted speckle images is more likely to be blurred by multiple scattering, resulting in decreased accuracy and spatial resolution of deep vessels. This study proposes a deep-learning-based strategy for high spatiotemporal res-olution three-dimensional (3D) reconstruction from a single transilluminated laser speckle contrast image, providing more structural and functional details without multifocus two-dimensional (2D) imaging or 3D optical imaging with point/line scanning. Based on the correlation transfer equa-tion, a large training dataset is generated by convolving vessel masks with depth-dependent point spread functions (PSF). The UNet and ResNet are used for deblurring and depth estimation. The blood flow in the reconstructed 3D vessels is estimated by a depth-dependent contrast model. The pro-posed method is evaluated with simulated data and phantom experiments, achieving high-fidelity structural reconstruc-tion with a depth-independent estimation of blood flow. This fast 3D blood flow imaging technique is suitable for real-time monitoring of thick tissue and the diagnosis of vascular dis-eases.& COPY; 2023 Optica Publishing Group