无需CT影像，用低剂量PET实现精准器官分割。
Self is the Best Learner: CT-free Ultra-Low-Dose PET Organ Segmentation via Collaborating Denoising and Segmentation Learning
- 利用自编码思想，让低剂量PET自己“补全”高剂量信息。
- 5%剂量下器官分割平均Dice达73.11%~73.97%，超越现有方法。
- 适合追求无创、低辐射医学影像分析的研究者。
正电子发射断层扫描（PET）中的器官分割对癌症定量至关重要。低剂量PET（LDPET）通过降低辐射暴露提供更安全的替代方案，但固有的噪声和模糊边界使分割更具挑战性。此外，现有方法依赖配准后的CT标注，忽视了模态不匹配问题。本文提出LDOS——一种无需CT的超低剂量PET器官分割新框架。受掩码自编码器启发，将低剂量PET视为全剂量PET的自然掩码版本。LDOS采用共享编码器提取通用特征，任务专用解码器分别优化去噪与分割输出。通过引入源自CT的器官标注辅助去噪过程，提升解剖边界识别能力并缓解PET/CT配准偏差。实验表明，在5%剂量条件下，对18个器官的分割平均Dice分数达到73.11%（18F-FDG）和73.97%（68Ga-FAPI），性能达当前最优。代码将于https://github.com/yezanting/LDOS公开。
原文摘要 · Abstract (English)
Organ segmentation in Positron Emission Tomography (PET) plays a vital role in cancer quantification. Low-dose PET (LDPET) provides a safer alternative by reducing radiation exposure. However, the inherent noise and blurred boundaries make organ segmentation more challenging. Additionally, existing PET organ segmentation methods rely on coregistered Computed Tomography (CT) annotations, overlooking the problem of modality mismatch. In this study, we propose LDOS, a novel CT-free ultra-LDPET organ segmentation pipeline. Inspired by Masked Autoencoders (MAE), we reinterpret LDPET as a naturally masked version of Full-Dose PET (FDPET). LDOS adopts a simple yet effective architecture: a shared encoder extracts generalized features, while task-specific decoders independently refine outputs for denoising and segmentation. By integrating CT-derived organ annotations into the denoising process, LDOS improves anatomical boundary recognition and alleviates the PET/CT misalignments. Experiments demonstrate that LDOS achieves state-of-the-art performance with mean Dice scores of 73.11% (18F-FDG) and 73.97% (68Ga-FAPI) across 18 organs in 5% dose PET. Our code will be available at https://github.com/yezanting/LDOS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。