Approximate k-space models and deep learning for fast photoacoustic reconstruction
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.
|Keywords||Compressed sensing, Fast fourier methods, Learned image reconstruction, Photoacoustic tomography|
|Series||Lecture Notes in Computer Science/Lecture Notes in Artificial Intelligence|
|Conference||International Workshop on Machine Learning for Medical Image Reconstruction, MLMIR|
Hauptmann, A, Cox, B.T, Lucka, F, Huynh, N, Betcke, M, Beard, P, & Arridge, S. (2018). Approximate k-space models and deep learning for fast photoacoustic reconstruction. In Machine Learning for Medical Image Reconstruction (pp. 103–111). doi:10.1007/978-3-030-00129-2_12