# Two-stage deep learning framework for the restoration of incomplete-ring PET images

arXiv: https://arxiv.org/abs/2504.00816 · HTML: https://mlsanity.com/paper/2504.00816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 78 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [Multiscale Structure Guided Diffusion for Image Deblurring](https://mlsanity.com/paper/2212.01789/) (2022)
- [PET image denoising based on denoising diffusion probabilistic models](https://mlsanity.com/paper/2209.06167/) (2022)
- [DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem](https://mlsanity.com/paper/1804.07851/) (2018)
- [Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion](https://mlsanity.com/paper/1711.10388/) (2017)
- [Score-Based Generative Models for PET Image Reconstruction](https://mlsanity.com/paper/2308.14190/) (2023)
- [Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise](https://mlsanity.com/paper/2311.14900/) (2023)
- [Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction](https://mlsanity.com/paper/2308.10157/) (2023)
- [Knowledge-driven deep learning for fast MR imaging: undersampled MR image reconstruction from supervised to un-supervised learning](https://mlsanity.com/paper/2402.02704/) (2024)
- [CG-3DSRGAN: A classification guided 3D generative adversarial network for image quality recovery from low-dose PET images](https://mlsanity.com/paper/2304.00725/) (2023)
- [Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data](https://mlsanity.com/paper/2309.06948/) (2023)

## Abstract (arXiv)

Positron Emission Tomography (PET) is an important molecular imaging tool widely used in medicine. Traditional PET systems rely on complete detector rings for full angular coverage and reliable data collection. However, incomplete-ring PET scanners have emerged due to hardware failures, cost constraints, or specific clinical needs. Standard reconstruction algorithms often suffer from performance degradation with these systems because of reduced data completeness and geometric inconsistencies. We present a two-stage deep-learning framework that, without incorporating any time-of-flight (TOF) information, restores high-quality images from data with about 50% missing coincidences - double the loss levels previously addressed by CNN-based methods. The pipeline operates in two stages: a projection-domain Attention U-Net first predicts the missing sections of the sinogram by leveraging spatial context from neighbouring slices, after which the completed data are reconstructed with OSEM algorithm and passed to a cascaded U-Net & warm-start diffusion model for image refinement. This module starts the reverse diffusion process from the U-Net coarse prediction rather than pure Gaussian noise. Using 613 simulated brain volumes from real scans (196 healthy brain samples, 217 Alzheimer's disease samples, and 200 Mild Cognitive Impairment samples), the result shows that our model successfully preserves most anatomical structures and tracer distribution features with PSNR of 38.18 to 38.59 dB and SSIM of 0.9904 to 0.9925. Our two-stage deep-learning framework effectively restores high-quality PET images from over 50% incomplete-ring data, achieving near-complete anatomical fidelity and robust performance without requiring TOF information.