Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning

TL;DR

This paper introduces a novel dynamical machine learning approach using a recurrent neural network to improve limited-angle tomographic reconstructions of dense layered objects, outperforming static methods in artifact reduction and fidelity.

Contribution

It presents a new dynamical system-based neural network method for tomographic reconstruction, leveraging angle sequences as a dynamical process, which enhances image quality over static prior-based methods.

Findings

Dynamic method reduces artifacts compared to static approaches.

Recurrent neural network improves reconstruction fidelity.

The approach is effective for strongly scattering layered objects.

Abstract

Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem with practical implications in medical and biological imaging, manufacturing, automation, and environmental and food security. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. Recently, it was shown that one effective way to learn the priors for strongly scattering yet highly structured 3D objects, e.g. layered and Manhattan, is by a static neural network [Goy et al, Proc. Natl. Acad. Sci. 116, 19848-19856 (2019)]. Here, we present a radically different approach where the collection of raw images from multiple angles is viewed analogously to a dynamical system driven by the object-dependent forward scattering operator. The sequence index in angle of illumination plays the role of discrete time in the dynamical system analogy. Thus, the imaging problem turns into a problem of nonlinear system identification, which also suggests dynamical learning as better fit to regularize the reconstructions. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the fundamental building block. Through comprehensive comparison of several quantitative metrics, we show that the dynamic method improves upon previous static approaches with fewer artifacts and better overall reconstruction fidelity.