# DirectPET: Full Size Neural Network PET Reconstruction from Sinogram Data

arXiv: https://arxiv.org/abs/1908.07516 · HTML: https://mlsanity.com/paper/1908.07516/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 9 of 9)

- [Direct PET Image Reconstruction Incorporating Deep Image Prior and a Forward Projection Model](https://mlsanity.com/paper/2109.00768/) (2021)
- [Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior](https://mlsanity.com/paper/2106.10359/) (2021)
- [List-Mode PET Image Reconstruction Using Deep Image Prior](https://mlsanity.com/paper/2204.13404/) (2022)
- [TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms](https://mlsanity.com/paper/2308.05365/) (2023)
- [PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstruction](https://mlsanity.com/paper/2605.08030/) (2026)
- [A Data-Driven Reconstruction Technique based on Newton's Method for Emission Tomography](https://mlsanity.com/paper/2110.11396/) (2021)
- [Masked Co-attentional Transformer reconstructs 100x ultra-fast/low-dose whole-body PET from longitudinal images and anatomically guided MRI](https://mlsanity.com/paper/2205.04044/) (2022)
- [Stretched sinograms for limited-angle tomographic reconstruction with neural networks](https://mlsanity.com/paper/2306.10201/) (2023)
- [End-to-End PET Image Reconstruction via a Posterior-Mean Diffusion Model](https://mlsanity.com/paper/2503.08546/) (2025)

## Abstract (arXiv)

Purpose: Neural network image reconstruction directly from measurement data is a relatively new field of research, that until now has been limited to producing small single-slice images (e.g., 1x128x128). This paper proposes a novel and more efficient network design for Positron Emission Tomography called DirectPET which is capable of reconstructing multi-slice image volumes (i.e., 16x400x400) from sinograms. Approach: Large-scale direct neural network reconstruction is accomplished by addressing the associated memory space challenge through the introduction of a specially designed Radon inversion layer. Using patient data, we compare the proposed method to the benchmark Ordered Subsets Expectation Maximization (OSEM) algorithm using signal-to-noise ratio, bias, mean absolute error and structural similarity measures. In addition, line profiles and full-width half-maximum measurements are provided for a sample of lesions. Results: DirectPET is shown capable of producing images that are quantitatively and qualitatively similar to the OSEM target images in a fraction of the time. We also report on an experiment where DirectPET is trained to map low count raw data to normal count target images demonstrating the method's ability to maintain image quality under a low dose scenario. Conclusion: The ability of DirectPET to quickly reconstruct high-quality, multi-slice image volumes suggests potential clinical viability of the method. However, design parameters and performance boundaries need to be fully established before adoption can be considered.