US 12,347,001 B2
System and method for PET-CT image artifact evaluation and correction
Raz Carmi, Haifa (IL)
Assigned to GE Precision Healthcare LLC, Wauwatosa, WI (US)
Filed by GE Precision Healthcare LLC, Wauwatosa, WI (US)
Filed on Aug. 8, 2022, as Appl. No. 17/882,784.
Prior Publication US 2024/0046535 A1, Feb. 8, 2024
Int. Cl. G06T 11/00 (2006.01); A61B 6/00 (2024.01); G06T 7/33 (2017.01)
CPC G06T 11/008 (2013.01) [A61B 6/5235 (2013.01); A61B 6/5264 (2013.01); G06T 7/344 (2017.01); G06T 2207/10081 (2013.01); G06T 2207/10104 (2013.01); G06T 2207/10108 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for automatic artifact evaluation and correction in medical imaging data, comprising:
obtaining, via a processor, emission-tomography functional image data and a corresponding reconstructed anatomical image volume of a subject, the emission-tomography functional image data and the corresponding reconstructed anatomical image volume comprising at least one organ having natural motion;
pre-determining, via the processor, a dedicated model for spatial mismatch correction of the at least one organ having natural motion;
performing, via the processor, initial image reconstruction of the emission-tomography functional image data to generate a reconstructed emission-tomography functional image volume utilizing attenuation correction based on the corresponding reconstructed anatomical image volume;
identifying, via the processor, relevant anatomical regions, within the reconstructed emission-tomography functional image volume and the corresponding reconstructed anatomical image volume, where functional image quality may be affected by the natural motion of the at least one organ;
identifying and evaluating, via the processor, potential attenuation-correction image artifacts in the reconstructed emission-tomography functional image volume that are related to functional-anatomical spatial mismatch;
estimating, via the processor, model parameters based on confirmed attenuation-correction image artifacts, wherein the model parameters represent the functional-anatomical spatial mismatch;
correcting, via the processor, the corresponding reconstructed anatomical image volume utilizing both the dedicated model and the model parameters to generate a corrected anatomical image volume; and
reconstructing, via the processor, the emission-tomography functional image data utilizing attenuation correction based on the corrected anatomical image volume to generate a corrected emission-tomography functional image volume.