Spatiotemporal PET reconstruction using ML-EM with learned diffeomorphic deformation

TL;DR

This paper introduces a scalable, deep learning-enhanced ML-EM algorithm for 3D PET reconstruction that effectively corrects for patient motion, reducing noise even with limited gated data.

Contribution

It presents a novel, scalable motion correction method combining ML-EM with unsupervised deep learning registration, suitable for high-resolution 3D PET imaging.

Findings

Significantly reduces noise with limited gated data

Scales well to 3D and higher resolutions

Maintains computational efficiency comparable to standard ML-EM

Abstract

Patient movement in emission tomography deteriorates reconstruction quality because of motion blur. Gating the data improves the situation somewhat: each gate contains a movement phase which is approximately stationary. A standard method is to use only the data from a few gates, with little movement between them. However, the corresponding loss of data entails an increase of noise. Motion correction algorithms have been implemented to take into account all the gated data, but they do not scale well, especially not in 3D. We propose a novel motion correction algorithm which addresses the scalability issue. Our approach is to combine an enhanced ML-EM algorithm with deep learning based movement registration. The training is unsupervised, and with artificial data. We expect this approach to scale very well to higher resolutions and to 3D, as the overall cost of our algorithm is only marginally greater than that of a standard ML-EM algorithm. We show that we can significantly decrease the noise corresponding to a limited number of gates.