PET/MR Attenuation Map Segmentation for Bone-Air Ambiguity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current MR imaging struggles to accurately differentiate between bone and air tissues due to low signal intensity, leading to challenges in quantification and segmentation, especially in PET/MR hybrid imaging systems where bone and air cavities exhibit similar signal intensities.
Innovation Solution
A method and system for segmenting bone and air in MR images using nuclear emission data, involving iterative reconstruction and attenuation correction, where specific attenuation coefficients are assigned to voxels in ambiguous regions, allowing for distinction between bone and air voxels through iterative updates of the attenuation map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional MR imaging is used to image bone and air, then the imaging process is simple and fast, but the signal intensity of cortical bone is low making it difficult to differentiate bone tissue from air cavities
Solution Approach 1:
The patent combines PET and MR imaging systems into a hybrid PET/MR imaging system. The PET component provides attenuation correction data that helps differentiate bone from air cavities, while the MR component provides soft tissue contrast. This merging of two imaging modalities resolves the contradiction by using PET's attenuation information to improve bone/air differentiation without requiring a completely new imaging device.
Solution Approach 2:
The patent uses attenuation correction maps generated from PET data as an intermediary to bridge the gap between MR imaging and accurate bone/air differentiation. The attenuation correction map serves as a mediator that provides additional information about tissue density and composition, enabling better segmentation of bone from air cavities while maintaining the simplicity of the MR imaging process.
2Reliability
If PET/MR hybrid imaging is used to improve soft-tissue contrast and reduce radiation exposure, then diagnostic quality improves, but the complexity of the imaging system and data processing increases
Solution Approach 1:
The patent segments the imaging process into distinct components: MR imaging for soft tissue contrast, PET imaging for attenuation correction, and a segmentation algorithm that combines both datasets. This segmentation allows the system to leverage the strengths of each modality while managing complexity through modular processing steps.
Solution Approach 2:
The patent changes parameters during the iterative reconstruction process, updating attenuation coefficients and tissue classification based on combined PET/MR data. By dynamically adjusting parameters such as attenuation correction factors and segmentation thresholds, the system achieves improved diagnostic accuracy while managing computational complexity through optimized parameter updates.
3Measurement precision
If iterative reconstruction with attenuation correction is applied to segment bone and air, then segmentation accuracy improves, but the computation time and processing complexity increase
Solution Approach 1:
The patent performs preliminary segmentation of the MR image into tissue classes before the iterative reconstruction process. This preliminary action provides initial estimates that guide the iterative optimization, reducing the number of iterations needed and thereby decreasing processing time while maintaining high segmentation precision.
Solution Approach 2:
The patent implements feedback mechanisms where the attenuation correction map is updated based on the PET data and used to refine the MR image segmentation in subsequent iterations. This feedback loop continuously improves segmentation accuracy while the iterative process is optimized to balance precision gains with computational time requirements.
Data Source
AI summary
A method for segmenting a medical image is disclosed. The method includes acquiring MR image and PET data during a scan of the object, acquiring an air/bone ambiguous region in the MR image, the air/bone ambiguous region including air voxels and bone voxels undistinguished from each other. The method also includes assigning attenuation coefficients to the voxels of the plurality of regions and generating an attenuation map. The method further includes iteratively reconstructing the PET data and the attenuation map to generate a PET image and an estimated attenuation map. The method further includes reassigning attenuation coefficients to the voxels of the air/bone ambiguous region based on the estimated attenuation map, and distinguishing the bone voxels and air voxels in the air/bone ambiguous region.