Generalizable CT-free PET attenuation and scatter correction via few-shot cross domain adaptation
Authors:
Open Access
- 14 May 2026
- journal article
- Published by Springer Nature in npj Digital Medicine
- Vol. 9 (1)
Abstract
The rapid advancements in PET technology, coupled with the need for accurate and efficient imaging, necessitate the development of robust and generalizable methods for CT-free attenuation and scatter correction (ASC). Deep learning offers a promising solution, but exhibits limited performance when tested in diverse clinical settings and varying imaging conditions. We propose a few-shot fine-tuning paradigm that enables efficient adaptation of models from a source domain to a new target domain. Our backbone network incorporates statistical modulation to extract domain-specific distribution information and employs pixel-wise factor scaling modeling to disentangle ASC factor maps from input images. On a large and diverse dataset of 1539 subjects across multiple tracers, scanners, and centers, we evaluate model performance under single-tracer training, multi-tracer joint training, and few-shot adaptation strategies. Although joint training demonstrates strong performance on known tracers, the proposed few-shot adaptation approach, CrossPET-Adapt, excels at adapting to unseen domains with minimal data, outperforming joint training. This method significantly reduces radiation exposure and data requirements, offering a rapid and robust solution for CT-free PET ASC in varied clinical environments.Keywords
Funding Information
- Shanghai Magnolia Talent Plan Pujiang Project (25PJD082)
- National Natural Science Foundation of China (62471299)
- National Natural Science Foundation of China (82372038)
- National Key Research and Development Program of China
- Natural Science Foundation of Guangdong Province in China (2023B1515120007)
- Shen- zhen Science, the Technology Program of China (KJZD20240903101307010)
- National Natu- ral Science Foundation of China project (UNNC Project ID B0166)
- Yongjiang Technology Innovation Project (2022A-097-G)
- Shanghai Municipal Key Clinical Specialty (shslczdzk03403)
This publication has 56 references indexed in Scilit:
- Projected Lifetime Cancer Risks From Current Computed Tomography ImagingJAMA Internal Medicine, 2025
- Strategies for deep learning‐based attenuation and scatter correction of brain 18F‐FDG PET images in the image domainMedical Physics, 2024
- Ultra‐low dose CT scanning for PET/CTMedical Physics, 2023
- Clinical performance of long axial field of view PET/CT: a head-to-head intra-individual comparison of the Biograph Vision Quadra with the Biograph Vision PET/CTEuropean Journal of Nuclear Medicine and Molecular Imaging, 2021
- Deep learning‐guided joint attenuation and scatter correction in multitracer neuroimaging studiesHuman Brain Mapping, 2020
- Deep-JASC: joint attenuation and scatter correction in whole-body 18F-FDG PET using a deep residual networkEuropean Journal of Nuclear Medicine and Molecular Imaging, 2020
- A Novel Loss Function Incorporating Imaging Acquisition Physics for PET Attenuation Map Generation Using Deep Learning2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Prognostic value of volumetric parameters of 18F-FDG PET in non-small-cell lung cancer: a meta-analysisEuropean Journal of Nuclear Medicine and Molecular Imaging, 2014
- PET attenuation coefficients from CT images: experimental evaluation of the transformation of CT into PET 511-keV attenuation coefficientsEuropean Journal of Nuclear Medicine and Molecular Imaging, 2002