Self-Supervised and Supervised Deep Learning for PET Image Reconstruction

TL;DR

This paper introduces a versatile deep learning framework for PET image reconstruction that combines self-supervised and supervised methods, adaptable to various data availability scenarios, and capable of producing high-quality images without extensive retraining.

Contribution

The authors develop a unified deep learning framework that integrates self-supervised and supervised approaches for PET reconstruction, capable of handling diverse training data conditions and enabling flexible, efficient image reconstruction.

Findings

Self-supervised networks perform well with minimal or no ground truth data.

Pretrained models can be used directly or fine-tuned for new datasets.

The framework demonstrates effective PET image reconstruction across different training scenarios.

Abstract

A unified self-supervised and supervised deep learning framework for PET image reconstruction is presented, including deep-learned filtered backprojection (DL-FBP) for sinograms, deep-learned backproject then filter (DL-BPF) for backprojected images, and a more general mapping using a deep network in both the sinogram and image domains (DL-FBP-F). The framework allows varying amounts and types of training data, from the case of having only one single dataset to reconstruct through to the case of having numerous measured datasets, which may or may not be paired with high-quality references. For purely self-supervised mappings, no reference or ground truth data are needed. The self-supervised deep-learned reconstruction operators all use a conventional image reconstruction objective within the loss function (e.g. maximum Poisson likelihood, maximum a posteriori). If it is desired for the reconstruction networks to generalise (i.e. to need either no or minimal retraining for a new measured dataset, but to be fast, ready to reuse), then these self-supervised networks show potential even when previously trained from just one single dataset. For any given new measured dataset, finetuning is however often necessary, and of course the initial training set should ideally go beyond just one dataset if a generalisable network is sought. Example results for the purely self-supervised single-dataset case are shown, but the networks can be i) trained uniquely for any measured dataset to reconstruct from, ii) pretrained on multiple datasets and then used with no retraining for new measured data, iii) pretrained and then finetuned for new measured data, iv) optionally trained with high-quality references. The framework, with its optional inclusion of supervised learning, provides a spectrum of reconstruction approaches by making use of whatever (if any) training data quantities and types are available.