Physiology-Guided Self-Supervised Learning for Simultaneous Dual-Tracer PET Separation

Yufei Jin; Hengjia Ran; Gaoning Ning; Xinhui Su; Min Guo; Wentao Zhu; Huafeng Liu

doi:10.1109/tmi.2026.3708472

June 30, 2026IEEE Transactions on Medical Imaging

Physiology-Guided Self-Supervised Learning for Simultaneous Dual-Tracer PET Separation

View at Publisher

Ask AI

Bookmark

Share

Key Points

To develop a physiology-guided self-supervised learning framework for separating overlapping signals in simultaneous dual-tracer PET scans without requiring paired single-tracer training labels.
Designed the DTPSS algorithm to decouple simultaneous dual-tracer emissions by integrating physiological kinetic constraints into a self-supervised neural network.
Evaluated model separation capabilities on real clinical data benchmarks, specifically testing protocols with tracers such as [18F]FAPI characterized by pronounced physiological variability.
Achieved superior signal separation performance compared with baseline methods under real-world data constraints lacking paired single-tracer ground-truth references.
Maintained robust separation fidelity despite significant inter-subject and intra-subject physiological variability in tracer kinetics.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Validation study demonstrates improved dual-tracer PET separation under real-world conditions without paired labels, suggesting enhanced multiplexed molecular imaging.

Abstract

F]FAPI), DTPSS achieved improved separation results under real-data settings with unavailable paired single-tracer labels and substantial physiological variability.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Jin et al. (2026) studied this question.

synapsesocial.com/papers/6a9c34183d2c6f73eaa6b8a1 https://doi.org/10.1109/tmi.2026.3708472

View at Publisher

Ask AI

Bookmark

Share

Physiology-Guided Self-Supervised Learning for Simultaneous Dual-Tracer PET Separation

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Physiology-Guided Self-Supervised Learning for Simultaneous Dual-Tracer PET Separation

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading