Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Generalizable CT-free PET attenuation and scatter correction via few-shot cross domain adaptation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月14日

查看全文
  • Hanzhong Wang,
  • Meiyuan Wen,
  • Xiaoya Qiao,
  • Qianhao Chen,
  • Yi An,
  • Xin Chen,
  • Rui Guo,
  • Qiu Huang,
  • Xiaohua Zhu,
  • Zhaoping Cheng,
  • Jiehua Xu,
  • Hairong Zheng,
  • Dong Liang,
  • Xiangjian He,
  • Zhanli Hu,
  • Biao Li

摘要

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.