Automatic Differentiation for Inverse Problems in X-ray Imaging and Microscopy

Life (Basel). 2023 Feb 23;13(3):629. doi: 10.3390/life13030629.

Abstract

Computational techniques allow breaking the limits of traditional imaging methods, such as time restrictions, resolution, and optics flaws. While simple computational methods can be enough for highly controlled microscope setups or just for previews, an increased level of complexity is instead required for advanced setups, acquisition modalities or where uncertainty is high; the need for complex computational methods clashes with rapid design and execution. In all these cases, Automatic Differentiation, one of the subtopics of Artificial Intelligence, may offer a functional solution, but only if a GPU implementation is available. In this paper, we show how a framework built to solve just one optimisation problem can be employed for many different X-ray imaging inverse problems.

Keywords: automatic differentiation; computational imaging; inverse problems; parameter refining; soft-X-ray microscopy.

Grants and funding

This research has been carried out within the Advanced Integrated Imaging Initiative (AI3)—project P2017004 of Elettra Sincrotrone Trieste.