MCP-Net: Introducing Patlak Loss Optimization to Whole-Body Dynamic PET Inter-Frame Motion Correction

• Published in: IEEE transactions on medical imaging Vol. 42; no. 12; pp. 3512 - 3523
• Main Authors: Guo, Xueqi, Zhou, Bo, Chen, Xiongchao, Chen, Ming-Kai, Liu, Chi, Dvornek, Nicha C.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Benchmarks; Deep learning; Dynamics; Error correction; Fitting; Image enhancement; Image reconstruction; Image warping; Inter-frame motion correction; Kinetic theory; Kinetics; Misalignment; Motion estimation; Motion simulation; Neural networks; Optimization; parametric imaging; Patlak loss optimization; Positron emission; Positron emission tomography; whole-body dynamic PET
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2023.3290003

In whole-body dynamic positron emission tomography (PET), inter-frame subject motion causes spatial misalignment and affects parametric imaging. Many of the current deep learning inter-frame motion correction techniques focus solely on the anatomy-based registration problem, neglecting the tracer kinetics that contains functional information. To directly reduce the Patlak fitting error for 18F-FDG and further improve model performance, we propose an inter-frame m otion c orrection framework with P atlak loss optimization integrated into the neural network (MCP-Net). The MCP-Net consists of a multiple-frame motion estimation block, an image-warping block, and an analytical Patlak block that estimates Patlak fitting using motion-corrected frames and the input function. A novel Patlak loss penalty component utilizing mean squared percentage fitting error is added to the loss function to reinforce the motion correction. The parametric images were generated using standard Patlak analysis following motion correction. Our framework enhanced the spatial alignment in both dynamic frames and parametric images and lowered normalized fitting error when compared to both conventional and deep learning benchmarks. MCP-Net also achieved the lowest motion prediction error and showed the best generalization capability. The potential of enhancing network performance and improving the quantitative accuracy of dynamic PET by directly utilizing tracer kinetics is suggested.