Synthetic CT Attenuation Mapping for PET Motion and Artifact Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Nuclear imaging systems face challenges in generating accurate attenuation maps, particularly when imaging high-density materials and encountering inter-scan motion and image artifacts, leading to inaccurate corrections.
Innovation Solution
The system generates synthetic computed tomography (CT) images using machine learning processes to create attenuation maps, employing image-to-image networks to generate initial and final synthetic images, determine regions of interest, and apply anatomical masks to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dual-energy CT systems are used to generate more accurate attenuation maps, then measurement precision is improved, but use of energy increases due to higher radiation doses
Solution Approach 1:
The patent uses generative adversarial networks to create synthetic dual-energy CT images from single-energy CT images. The GAN learns the mapping between single-energy and dual-energy image spaces, generating realistic multi-energy images without requiring additional radiation exposure. This copying approach preserves the attenuation information needed for accurate correction while avoiding the harmful radiation of actual dual-energy scanning.
Solution Approach 2:
The system changes the energy parameter of CT images through machine learning transformation rather than physical dual-energy scanning. The GAN model transforms single-energy images into synthetic multi-energy images by learning the statistical relationships between different energy levels, effectively changing the energy parameter without additional radiation exposure.
2Use of energy by moving object
If single-energy CT images are used to generate attenuation maps, then use of energy is reduced, but measurement precision deteriorates due to inaccurate corrections with high density materials
Solution Approach 1:
The patent generates synthetic dual-energy images that copy the information content of real dual-energy scans from single-energy input. The GAN creates realistic multi-energy representations that preserve the attenuation characteristics of high-density materials, enabling accurate correction while using only single-energy radiation exposure.
3Measurement precision
If image-to-image network processes are applied to generate synthetic images, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent replaces complex physical dual-energy scanning mechanisms with machine learning-based image transformation. Instead of using hardware to generate multi-energy images, the system uses trained GAN models to synthetically generate them, substituting mechanical complexity with computational processing that can be performed on standard computing hardware.
Data Source
AI summary
Systems and methods for generating attenuation maps for reconstructing medical images are disclosed. In some examples, measurement data, such as positron emission tomography (PET) data or single-photon emission computed tomography (SPECT) data, is received for a subject. A machine learning process is applied to the measurement data to generate initial synthetic images for multiple values of an imaging parameter. Further, patient data is received and classified to determine an object imaged with the subject. A second medical image is selected that includes the object, and a region-of-interest (ROI) of the initial synthetic images is determined. Further, based on the ROI an anatomical mask is generated for each initial synthetic image. A second image-to-image network process is applied to the patient data, the second medical image, a portion of each initial synthetic image that includes the ROI, and the corresponding anatomical mask to generate a final synthetic image.