小肿瘤分割无需长程建模，局部交互更有效
Is Long Range Sequential Modeling Necessary For Colorectal Tumor Segmentation?
- 用MambaOutUNet聚焦局部特征，替代全局建模
- 在CTS-204数据集上精度超越传统长程模型
- 适合小而复杂的肿瘤分割任务研究者参考
结直肠癌（CRC）三维医学影像中的肿瘤分割既复杂又临床关键，对放疗规划和生存率评估至关重要。近期，采用长程序列建模机制（如Transformer、Mamba）的3D体积分割架构因其高精度备受关注。本文通过对比我们提出的MambaOutUNet与这些全局建模方法，在新构建的结直肠肿瘤分割数据集CTS-204上进行评估。结果表明，在目标区域小且解剖结构复杂的情况下，强大的局部特征交互可优于长程建模技术，提示3D肿瘤分割研究可能需转向更注重局部建模的范式。
原文摘要 · Abstract (English)
Segmentation of colorectal cancer (CRC) tumors in 3D medical imaging is both complex and clinically critical, providing vital support for effective radiation therapy planning and survival outcome assessment. Recently, 3D volumetric segmentation architectures incorporating long-range sequence modeling mechanisms, such as Transformers and Mamba, have gained attention for their capacity to achieve high accuracy in 3D medical image segmentation. In this work, we evaluate the effectiveness of these global token modeling techniques by pitting them against our proposed MambaOutUNet within the context of our newly introduced colorectal tumor segmentation dataset (CTS-204). Our findings suggest that robust local token interactions can outperform long-range modeling techniques in cases where the region of interest is small and anatomically complex, proposing a potential shift in 3D tumor segmentation research.
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。