Paper Proffered Program Radiopharmaceuticals, Theranostics, and Nuclear Medicine

Foundation Model-Guided PET Imaging for Low-Dose Acquisition and Inter-Radiotracer Translation

Abstract
Purpose

Low-count PET acquisition and inter-radiotracer translation offer effective strategies to reduce radiation dose and mitigate tracer availability constraints. Recent self-supervised learning (SSL) foundation models (e.g., DINOv3) have demonstrated strong ability to extract high-level semantic representations in medical imaging when trained at scale; however, their application to PET imaging remains largely unexplored due to the limited availability of large PET datasets. This study proposes a DINOv3-guided PET imaging framework for low-dose reconstruction and inter-radiotracer translation.

Methods

Two paired PET datasets were used: (1) an institutional whole-body PET dataset comprising 35 full-count scans with one-eighth simulated low-count reconstructions, and (2) an inter-radiotracer brain PET imaging dataset from ADNI including 192 paired FDG and amyloid targeted AV45 scans. A dual-encoder U-Net architecture was developed, comprising a trainable ViT-B encoder and a frozen ViT-B encoder initialized with CT-pretrained DINOv3 weights. Multi-level features from both encoders were concatenated and forwarded to a transformer-based decoder for image reconstruction. Model training used a weighted combination of L1 reconstruction loss, perceptual LPIPS loss, and adversarial GAN loss. Ablation studies were performed by removing the DINOv3 encoder branch. Image quality was quantitatively evaluated using structural similarity index (SSIM), peak signal-to-noise ratio (PSNR) and normalized mean absolute error (NMAE).

Results

For low-count reconstruction, SSIM/PSNR/NMAE improved from 0.71/23.60 dB/0.04 to 0.77/24.84 dB/0.03 (p < 0.01, p < 0.05, and not statistically significant, respectively). For inter-radiotracer translation, SSIM/PSNR/NMAE improved from 0.63/15.97 dB/0.07 to 0.73/20.12 dB/0.04 (all p < 0.001). Meanwhile, the proposed method reduced noise in low-count reconstruction and preserved gray-to-white matter uptake patterns in inter-tracer translation.

Conclusion

This work presents the first foundation-model-guided framework for PET imaging across multiple tasks. Results demonstrate that transferable semantic representations derived from non-PET-pretrained encoders can significantly improve supervised PET image synthesis performance, providing a promising pathway toward general-purpose, multi-task PET foundation models.

People

Related

Similar sessions

Poster Poster Program
Jul 19 · 07:00
Adverse Events in Targeted Radionuclide Therapy

Radiopharmaceutical therapy (RPT) plays an important role in the management of oncology patients, particularly those with thyroid cancer, prostate cancer, and neuroendocrine tumor. The use of radionuclide therapy has expanded rap...

Harrison L. Agordzo
Radiopharmaceuticals, Theranostics, and Nuclear Medicine 0 people interested
Poster Poster Program
Jul 19 · 07:00
Development of a Web-Based Theranostic Workflow Management Tool

To develop a Web-Based Theranostic Workflow Management Tool (TWMT) to efficiently manage Theranostic program in the department of radiation oncology (RadOnc).

Ling Zhuang, PhD
Radiopharmaceuticals, Theranostics, and Nuclear Medicine 0 people interested
Poster Poster Program
Jul 19 · 07:00
Epidseg-Net:the Multi-Modal Fusion Framework Based on Drr Guidance In Radiotherapy Is Used for Precise Segmentation of Epid Lung Targets

The proposed multimodal segmentation framework, named EPIDSeg-Net, comprises an encoder, a multi-scale feature layer, and a decoder. The encoder utilizes a dual-branch architecture: a CNN branch for extracting local texture featu...

Huang Qian Qianjia, M.Eng
Radiopharmaceuticals, Theranostics, and Nuclear Medicine 0 people interested