用3D Swin Transformer提升癌症PET/CT图像病灶分割精度
Lesion Segmentation in FDG-PET/CT Using Swin Transformer U-Net 3D: A Robust Deep Learning Framework
- 结合滑动窗口注意力与U-Net跳跃连接，兼顾全局上下文与细节
- 在AutoPET III数据集上达Dice 0.88、IoU 0.78，显著优于传统模型
- 适合放射科医生和医学影像研究者，尤其关注小病灶检测
正电子发射断层扫描/计算机断层扫描（PET/CT）中准确自动的病灶分割对癌症诊断和治疗规划至关重要。本文提出一种基于Swin Transformer的3D U-Net框架（SwinUNet3D），用于氟脱氧葡萄糖正电子发射断层扫描/计算机断层扫描（FDG-PET/CT）中的病灶分割。通过结合滑动窗口自注意力机制与U-Net风格的跳跃连接，该模型同时捕捉全局上下文信息与精细解剖结构。在AutoPET III FDG数据集上的评估显示，SwinUNet3D的Dice分数为0.88，交并比（IoU）为0.78，显著优于基准3D U-Net（Dice 0.48，IoU 0.32），且推理速度更快。定性分析表明，其对小病灶和不规则病灶的检测能力更强，假阳性减少，且更精确地实现PET/CT图像融合。尽管当前框架仅限于FDG扫描且在有限GPU资源下训练，但为未来多示踪剂、多中心评估及与其他基于Transformer的架构对比奠定了坚实基础。总体而言，SwinUNet3D是一种高效稳健的PET/CT病灶分割方法，推动了Transformer模型在肿瘤影像工作流中的应用。
原文摘要 · Abstract (English)
Accurate and automated lesion segmentation in Positron Emission Tomography / Computed Tomography (PET/CT) imaging is essential for cancer diagnosis and therapy planning. This paper presents a Swin Transformer UNet 3D (SwinUNet3D) framework for lesion segmentation in Fluorodeoxyglucose Positron Emission Tomography / Computed Tomography (FDG-PET/CT) scans. By combining shifted window self-attention with U-Net style skip connections, the model captures both global context and fine anatomical detail. We evaluate SwinUNet3D on the AutoPET III FDG dataset and compare it against a baseline 3D U-Net. Results show that SwinUNet3D achieves a Dice score of 0.88 and IoU of 0.78, surpassing 3D U-Net (Dice 0.48, IoU 0.32) while also delivering faster inference times. Qualitative analysis demonstrates improved detection of small and irregular lesions, reduced false positives, and more accurate PET/CT fusion. While the framework is currently limited to FDG scans and trained under modest GPU resources, it establishes a strong foundation for future multi-tracer, multi-center evaluations and benchmarking against other transformer-based architectures. Overall, SwinUNet3D represents an efficient and robust approach to PET/CT lesion segmentation, advancing the integration of transformer-based models into oncology imaging workflows.
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。