Physiological neural representation for personalised tracer kinetic parameter estimation from dynamic PET

2025-04-23

AI Summary

To address the high computational cost, low spatial resolution, and heavy reliance on large-scale annotated data in dynamic PET-based personalized tracer kinetic parameter estimation, this paper proposes a physiological neural representation framework based on implicit neural representations (INRs). The method jointly models PET and CT by integrating anatomical priors from a pre-trained 3D CT foundation model with a two-compartment kinetic model (TCKM). It requires no large annotated training dataset, significantly reduces computational overhead, and enables sub-voxel high-resolution parametric mapping. In tumor and highly vascularized regions, the approach improves anatomical consistency and spatial resolution, achieving substantially lower mean squared error compared to state-of-the-art deep learning methods. The framework robustly supports tumor characterization, automated segmentation, and prognostic assessment.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Motion & Tracking

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Dynamic positron emission tomography (PET) with [$^{18}$F]FDG enables non-invasive quantification of glucose metabolism through kinetic analysis, often modelled by the two-tissue compartment model (TCKM). However, voxel-wise kinetic parameter estimation using conventional methods is computationally intensive and limited by spatial resolution. Deep neural networks (DNNs) offer an alternative but require large training datasets and significant computational resources. To address these limitations, we propose a physiological neural representation based on implicit neural representations (INRs) for personalized kinetic parameter estimation. INRs, which learn continuous functions, allow for efficient, high-resolution parametric imaging with reduced data requirements. Our method also integrates anatomical priors from a 3D CT foundation model to enhance robustness and precision in kinetic modelling. We evaluate our approach on an [$^{18}$F]FDG dynamic PET/CT dataset and compare it to state-of-the-art DNNs. Results demonstrate superior spatial resolution, lower mean-squared error, and improved anatomical consistency, particularly in tumour and highly vascularized regions. Our findings highlight the potential of INRs for personalized, data-efficient tracer kinetic modelling, enabling applications in tumour characterization, segmentation, and prognostic assessment.

Problem

• Estimating personalized tracer kinetic parameters from dynamic PET data
• Reducing computational intensity and data requirements for parameter estimation
• Enhancing spatial resolution and anatomical consistency in kinetic modeling

Innovation

• Uses implicit neural representations for parameter estimation
• Integrates anatomical priors from 3D CT model
• Achieves high-resolution imaging with less data