Multi-Frame Deconvolution (MF-Decon)

Project – Enhancing super-resolution localisation ultrasound microscopy with model-based and data-driven approaches.

A Multi-Frame Deconvolution (MF-Decon) framework that can exploit the spatiotemporal coherence inherent in the CEUS data has been proposed, with new spatial and temporal regularisers designed based on total variation (TV) and regularisation by denoising (RED). Based on the MF-Decon framework, we introduce two novel methods: MF-Decon with spatial and temporal TVs (MF-Decon+3DTV) and MF-Decon with spatial RED and temporal TV (MF-Decon+RED+TV). Results from in silico simulations and in vivo rat brain dataset both indicate that our methods outperform two widely used methods using deconvolution or normalised cross-correlation.

Currently, we are still exploiting the application of neural networks on the super-resolution ultrasound imaging. Preliminary results demonstrate the huge potential of generating the microvasculature images of animal and human organs with much better qualities.