DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem

Abstract

Positron emission tomography (PET) is a cornerstone of modern radiology. The ability to detect cancer and metastases in whole body scans fundamentally changed cancer diagnosis and treatment. One of the main bottlenecks in the clinical application is the time it takes to reconstruct the anatomical image from the deluge of data in PET imaging. State-of-the art methods based on expectation maximization can take hours for a single patient and depend on manual fine-tuning. This results not only in financial burden for hospitals but more importantly leads to less efficient patient handling, evaluation, and ultimately diagnosis and treatment for patients. To overcome this problem we present a novel PET image reconstruction technique based on a deep convolutional encoder-decoder network, that takes PET sinogram data as input and directly outputs full PET images. Using realistic simulated data, we demonstrate that our network is able to reconstruct images >100 times faster, and with comparable image quality (in terms of root mean squared error) relative to conventional iterative reconstruction techniques.

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Convolutional Neural Network Based Metal Artifact Reduction in X-ray Computed Tomography
• 3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network
• CNN-Based Projected Gradient Descent for Consistent Image Reconstruction
• Iterative PET Image Reconstruction Using Convolutional Neural Network Representation

Cited by in corpus (23)

• Full-count PET Recovery from Low-count Image Using a Dilated Convolutional Neural Network
• Anatomical-Guided Attention Enhances Unsupervised PET Image Denoising Performance
• Direct PET Image Reconstruction Incorporating Deep Image Prior and a Forward Projection Model
• List-Mode PET Image Reconstruction Using Deep Image Prior
• Fully 3D Implementation of the End-to-end Deep Image Prior-based PET Image Reconstruction Using Block Iterative Algorithm
• TransEM:Residual Swin-Transformer based regularized PET image reconstruction
• Quantitative Comparison of Planar Coded Aperture Imaging Reconstruction Methods
• Medical Imaging Synthesis using Deep Learning and its Clinical Applications: A Review
• Technical Report: Towards Spatial Feature Regularization in Deep-Learning-Based Array-SAR Reconstruction
• Deep Learning for Biomedical Image Reconstruction: A Survey
• Direct mapping from PET coincidence data to proton-dose and positron activity using a deep learning approach
• A Symmetric Encoder-Decoder with Residual Block for Infrared and Visible Image Fusion
• FastPET: Near Real-Time PET Reconstruction from Histo-Images Using a Neural Network
• A Novel Implicit Neural Representation for Volume Data
• ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection
• Machine Learning in Quantitative PET Imaging
• TOF MLEM Adaptation for the Total-Body J-PET with a Realistic Analytical System Response Matrix
• Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding
• Interpretable Modeling and Reduction of Unknown Errors in Mechanistic Operators
• Artificial Intelligence-Guided PET Image Reconstruction and Multi-Tracer Imaging: Novel Methods, Challenges, And Opportunities
• Improved low-count quantitative PET reconstruction with an iterative neural network
• FA-GAN: Fused Attentive Generative Adversarial Networks for MRI Image Super-Resolution
• A General Framework for Inverse Problem Solving using Self-Supervised Deep Learning: Validations in Ultrasound and Photoacoustic Image Reconstruction