Validation of a Deep-Learning Coregistration Framework for Long-Axial-Field-of-View PET/CT Using Low-Radiation-Exposure Protocols Across Various Tracers

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: Consistent similarity metrics when comparing low-count reconstructed CT with reference CT

• Primary Outcome: Robust coregistration performance across reduced PET counts and ultra-low-dose CT conditions

• Nnt Or Sensitivity: Maintained quantitative accuracy across varying dose conditions as measured by SUV consistency

• Confidence Interval: Not reported in abstract

Clinical Application

Requires LAFOV PET/CT systems and deep-learning computational infrastructure Relevant for Australian nuclear medicine departments with LAFOV systems. Supports ACPSEM radiation protection principles and could facilitate TGA-approved low-dose protocols Patients requiring PET/CT imaging where radiation dose reduction is prioritised, particularly in research settings and vulnerable populations

Abstract

The advent of long-axial-field-of-view (LAFOV) PET/CT systems has significantly improved whole-body imaging by providing higher sensitivity and extended torso coverage. However, PET/CT potential misalignment remains a challenge, potentially introducing artifacts and quantification errors. Moreover, PET protocols with reduced scanning duration and dose, as well as the use of ultra-low-dose CT (ULD-CT), are increasingly relevant in clinical practice and research. This study aimed to evaluate the robustness and generalizability of a deep-learning coregistration framework for PET/CT alignment using low-dose PET and ULD-CT across various tracers with a LAFOV system. Methods: In total, 63 scans with 4 different tracers (89Zr-trastuzumab, 15O-H2O, 18F-MC225, and 18F-FDG) were included to assess PET and CT alignment improvements. Further evaluation was performed by comparing CT scans coregistered to the original PET images (rCT) with those coregistered to low-count (50%, 25%, and 12.5% of original counts) PET images (LC-rCT). Dice similarity coefficient, Jaccard similarity coefficient, Hausdorff distance, and average surface distance were used as evaluation metrics. Furthermore, ULD-CT coregistered to PET (rULD-CT) was compared with low-dose CT coregistered to the same PET (rLD-CT) using the same metrics. PET accuracy was evaluated by calculating SUVs. Results: The robustness of the deep-learning coregistration framework was demonstrated in reduced PET counts and ULD-CT scenarios across tracers. All metrics indicated robust performance when comparing LC-rCT with rCT and rULD-CT with rLD-CT. Consistent SUVs across varying PET counts and ULD-CT conditions further validated the quantitative accuracy of the approach. Conclusion: This work highlights that neither the use of low-dose PET protocols nor ULD-CT compromise the performance of this coregistration framework across 4 tracers. For LAFOV PET, these findings support the feasibility of such a framework in imaging protocols with reduced radiation exposure.

References

1. 1.Li, Z., Providência, L., Mohr, P., Mostafapour, S., Roya, M., Martinez-Lucio, T. S., Somsen, J. F., van Leeuwen, G. L., Salvi De Souza, G., van Sluis, J., Glaudemans, A. W. J. M., Dierckx, R. A. J. O., de Vries, J.-P. P. M., Luurtsema, G., Slart, R. H. J. A., Brouwers, A. H., Schleyer, P., Conti, M., Lammertsma, A. A., Schaefferkoetter, J., & Tsoumpas, C. (2026). Validation of a deep-learning coregistration framework for long-axial-field-of-view PET/CT using low-radiation-exposure protocols across various tracers. *Journal of Nuclear Medicine*, *67*(5). https://doi.org/10.2967/jnumed.125.270420