Approximate k-space models and Deep Learning for fast photoacoustic reconstruction
This work addresses the need for faster image reconstruction in medical imaging, specifically for photoacoustic tomography, though it is incremental as it builds on existing k-space and deep learning methods.
The authors tackled the problem of slow iterative reconstructions in photoacoustic tomography by developing a framework that combines an approximate k-space forward model with a CNN to correct aliasing artefacts, achieving a 32 times speed-up and superior results compared to total variation reconstructions in human in-vivo measurements.
We present a framework for accelerated iterative reconstructions using a fast and approximate forward model that is based on k-space methods for photoacoustic tomography. The approximate model introduces aliasing artefacts in the gradient information for the iterative reconstruction, but these artefacts are highly structured and we can train a CNN that can use the approximate information to perform an iterative reconstruction. We show feasibility of the method for human in-vivo measurements in a limited-view geometry. The proposed method is able to produce superior results to total variation reconstructions with a speed-up of 32 times.