PET Image Reconstruction Using MLAA with TOF and Deep Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current positron emission tomography (PET) systems require additional scans like CT or MRI to obtain high-quality attenuation images, leading to increased radiation exposure and difficulties in image reconstruction due to crosstalk artifacts and noise.
Innovation Solution
A deep learning algorithm-based positron emission tomography system that generates high-quality attenuation and emission images solely from PET data using Maximum Likelihood reconstruction of Attenuation and Activity with Time-Of-Flight (MLAA with TOF), which includes a collection unit, generation unit, and a learning unit to adjust weights and reduce errors, thereby eliminating the need for separate scans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional CT or MRI scan is performed to obtain attenuation image, then image quality is improved, but radiation exposure to patient increases
Solution Approach 1:
The patent combines the attenuation image acquisition and emission image acquisition into a single PET scan process using the MLAA algorithm. Instead of performing separate CT/MRI scans for attenuation correction, the system simultaneously reconstructs both attenuation and emission images from the same PET data, eliminating the need for additional scanning and thus reducing radiation exposure while maintaining image quality.
Solution Approach 2:
The PET scan system is made multi-functional by enabling it to perform both attenuation image acquisition and emission image acquisition through the MLAA reconstruction algorithm. The single PET scanner serves dual purposes: obtaining the attenuation map for correction and the emission data for functional imaging, replacing the need for separate dedicated CT or MRI equipment for attenuation correction.
2Loss of time
If MLAA with TOF is used to simultaneously obtain attenuation and emission images, then additional scan is eliminated, but image quality deteriorates due to crosstalk artifacts and noise
Solution Approach 1:
The patent employs an iterative reconstruction algorithm where the reconstructed emission image and attenuation image are continuously refined through multiple iterations. The algorithm uses feedback from the reconstructed images to update the estimation of attenuation and activity distributions, progressively reducing crosstalk artifacts and noise while converging to accurate solutions that satisfy both the PET measurement equations and anatomical constraints.
Solution Approach 2:
The system optimizes reconstruction parameters including the number of iterations, regularization strength, and time-of-flight window settings to balance image quality and computational efficiency. By adjusting these parameters, the algorithm can suppress noise and crosstalk artifacts while maintaining the speed advantage of simultaneous reconstruction, allowing flexible control over the trade-off between image quality and processing time.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach minimizes radiation exposure, reduces reconstruction time and cost, and improves image quality by effectively addressing noise and crosstalk artifacts, resulting in high-quality attenuation and emission images.
Implementation Method 1
a positron emission tomography (PET) device needs to perform a process of correcting and reconstructing an image in order to check at which portion of a body the radiopharmaceuticals are collected from raw data by detecting two disappearing radiations (gamma rays) emitted from the positron
Implementation Method 2
a simultaneous reconstruction algorithm (Maximum Likelihood reconstruction of Attenuation and Activity with Time-Of-Flight, MLAA with TOF) which can simultaneously obtain an attenuation image (μ-MLAA) and an emission image (λ-MLAA)
Data Source
AI summary
Disclosed are a positron emission tomography system and an image reconstructing method using the same and the positron emission tomography system includes: a collection unit collecting a positron emission tomography sinogram (PET sinogram); an image generation unit applying the positron emission tomography sinogram to an MLAA with TOF and generating a first emission image and a first attenuation image; and a control unit selecting at least one of the first emission image and the first attenuation image generated by the image generation unit as an input image and generating and providing a final attenuation image by applying the input image to the learned deep learning algorithm.