一个模型同时搞定脑部MRI和肺部CT肿瘤分割，效果稳定。
A Unified Attention U-Net Framework for Cross-Modality Tumor Segmentation in MRI and CT
- 用统一网络+注意力跳跃连接，跨模态共享特征
- 在两种影像上均达高精度，Dice超0.85，性能稳定
- 无需额外调参或适配，适合多模态医学图像研究
本研究提出一种统一的注意力U-Net架构，联合训练于脑部MRI（BraTS 2021）与肺部CT（LIDC-IDRI）数据集，探索单一模型在不同成像模态和解剖部位间的泛化能力。所提方法包含模态和谐预处理、注意力门控跳跃连接及模态感知的焦点Tversky损失函数。据我们所知，这是首个在独立的MRI（BraTS）与CT（LIDC-IDRI）数据集上联合训练单个Attention U-Net的研究，不依赖模态专用编码器或领域自适应技术。该统一模型在两个域上均展现出优异的分割性能，Dice系数、交并比（IoU）和受试者工作特征曲线下面积（AUC）表现俱佳，为未来跨模态肿瘤分割研究建立了可靠且可复现的基准。
原文摘要 · Abstract (English)
This study presents a unified Attention U-Net architecture trained jointly on MRI (BraTS 2021) and CT (LIDC-IDRI) datasets to investigate the generalizability of a single model across diverse imaging modalities and anatomical sites. Our proposed pipeline incorporates modality-harmonized preprocessing, attention-gated skip connections, and a modality-aware Focal Tversky loss function. To the best of our knowledge, this study is among the first to evaluate a single Attention U-Net trained simultaneously on separate MRI (BraTS) and CT (LIDC-IDRI) tumor datasets, without relying on modality-specific encoders or domain adaptation. The unified model demonstrates competitive performance in terms of Dice coefficient, IoU, and AUC on both domains, thereby establishing a robust and reproducible baseline for future research in cross-modality tumor segmentation.
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。