Filling of incomplete sinograms from sparse PET detector configurations using a residual U-Net

2025-06-24

AI Summary

Long axial-field-of-view (LAFOV) PET systems suffer from severe sinogram undersampling—e.g., 50% detector removal yielding only 25% of valid lines-of-response—due to sparse detector configurations, leading to substantial image quality degradation. To address this, we propose an enhanced residual U-Net deep learning framework, the first end-to-end sinogram completion method specifically designed for clinical PET data. Trained and validated on real-world clinical scans, our model significantly outperforms conventional 2D interpolation in both sinogram and reconstructed image domains: mean absolute error < 2 counts/pixel, with markedly improved structural fidelity and quantitative accuracy. This approach establishes a novel, empirically validated paradigm for reducing hardware costs in whole-body PET systems and accelerating the clinical translation of sparse-detector architectures.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Learning & Optimization for CV
• Reasoning under Uncertainty: Graphical Models

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Long axial field-of-view PET scanners offer increased field-of-view and sensitivity compared to traditional PET scanners. However, a significant cost is associated with the densely packed photodetectors required for the extended-coverage systems, limiting clinical utilisation. To mitigate the cost limitations, alternative sparse system configurations have been proposed, allowing an extended field-of-view PET design with detector costs similar to a standard PET system, albeit at the expense of image quality. In this work, we propose a deep sinogram restoration network to fill in the missing sinogram data. Our method utilises a modified Residual U-Net, trained on clinical PET scans from a GE Signa PET/MR, simulating the removal of 50% of the detectors in a chessboard pattern (retaining only 25% of all lines of response). The model successfully recovers missing counts, with a mean absolute error below two events per pixel, outperforming 2D interpolation in both sinogram and reconstructed image domain. Notably, the predicted sinograms exhibit a smoothing effect, leading to reconstructed images lacking sharpness in finer details. Despite these limitations, the model demonstrates a substantial capacity for compensating for the undersampling caused by the sparse detector configuration. This proof-of-concept study suggests that sparse detector configurations, combined with deep learning techniques, offer a viable alternative to conventional PET scanner designs. This approach supports the development of cost-effective, total body PET scanners, allowing a significant step forward in medical imaging technology.

Problem

• Recover missing PET sinogram data from sparse detectors
• Reduce costs of long axial PET scanners using deep learning
• Improve image quality in sparse detector PET configurations

Innovation

• Residual U-Net restores sparse PET sinograms
• Deep learning compensates for detector undersampling
• Chessboard detector pattern reduces PET system cost