Implantation of an Artificial Intelligence Denoising Algorithm Using SubtlePET™ with Various Radiotracers: 18F-FDG, 68Ga PSMA-11 and 18F-FDOPA, Impact on the Technologist Radiation Doses

TL;DR

This study shows that using an AI algorithm called SubtlePET™ improves PET image quality while reducing radiation doses and scan time for various radiotracers.

Contribution

The novel contribution is demonstrating the clinical effectiveness of SubtlePET™ across multiple radiotracers with significant dose reduction and improved image quality.

Findings

SubtlePET™ enabled dose reductions exceeding 33% and time savings of over 25%.

AI-enhanced images were rated interpretable in 100% of cases versus 65% for standard low-dose reconstructions.

Quantitative image quality improved significantly with SNR and CNR gains of 50–70%.

Abstract

This study assesses the clinical deployment of SubtlePET™, a commercial AI-based denoising algorithm, across three radiotracers—18F-FDG, 68Ga-PSMA-11, and 18F-FDOPA—with the goal of improving image quality while reducing injected activity, technologist radiation exposure, and scan time. A retrospective analysis on a digital PET/CT system showed that SubtlePET™ enabled dose reductions exceeding 33% and time savings of over 25%. AI-enhanced images were rated interpretable in 100% of cases versus 65% for standard low-dose reconstructions. Notably, 85% of AI-enhanced scans received the maximum Likert quality score (5/5), indicating excellent diagnostic confidence and noise suppression, compared to only 50% with conventional reconstruction. The quantitative image quality improved significantly across all tracers, with SNR and CNR gains of 50–70%. Radiotracer dose reductions were particularly substantial in low-BMI patients (up to 41% for FDG), and the technologist exposure decreased for high-exposure roles. The daily patient throughput increased by an average of 4.84 cases. These findings support the robust integration of SubtlePET™ into routine clinical PET practice, offering improved efficiency, safety, and image quality without compromising lesion detectability.

Figures