用旋转位置编码提升3D医学图像分割泛化能力
RoMedFormer: A Rotary-Embedding Transformer Foundation Model for 3D Genito-Pelvic Structure Segmentation in MRI and CT
- 基于旋转位置编码的Transformer架构，增强3D空间特征表示
- 在多模态MRI/CT数据上预训练，下游分割性能显著提升
- 适合需要跨模态、跨个体泛化的医疗影像分析任务
基于深度学习的女性生殖盆腔结构在MRI和CT中的分割对放疗、手术规划和疾病诊断至关重要。然而，现有分割模型在跨成像模态和解剖变异下的泛化能力有限。本文提出RoMedFormer，一种基于旋转位置嵌入的Transformer基础模型，用于3D女性生殖盆腔结构分割。该模型通过自监督学习和旋转位置编码，增强了3D医学数据的空间特征表达并捕捉长程依赖关系。我们在包含多种3D MRI和CT扫描的多样化数据集上进行预训练，并在下游分割任务中微调。实验结果表明，RoMedFormer在生殖盆腔器官分割上表现优异。研究验证了Transformer架构在医学图像分割中的潜力，为更具迁移性的分割框架提供了新方向。
原文摘要 · Abstract (English)
Deep learning-based segmentation of genito-pelvic structures in MRI and CT is crucial for applications such as radiation therapy, surgical planning, and disease diagnosis. However, existing segmentation models often struggle with generalizability across imaging modalities, and anatomical variations. In this work, we propose RoMedFormer, a rotary-embedding transformer-based foundation model designed for 3D female genito-pelvic structure segmentation in both MRI and CT. RoMedFormer leverages self-supervised learning and rotary positional embeddings to enhance spatial feature representation and capture long-range dependencies in 3D medical data. We pre-train our model using a diverse dataset of 3D MRI and CT scans and fine-tune it for downstream segmentation tasks. Experimental results demonstrate that RoMedFormer achieves superior performance segmenting genito-pelvic organs. Our findings highlight the potential of transformer-based architectures in medical image segmentation and pave the way for more transferable segmentation frameworks.
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。