用切比雪夫KAN+视觉LSTM提升3D医学图像分割精度
UNetVL: Enhancing 3D Medical Image Segmentation with Chebyshev KAN Powered Vision-LSTM
- 融合切比雪夫KAN与视觉LSTM，增强长程依赖建模能力
- 在ACDC和AMOS2022上分别提升7.3%和15.6%的Dice分数
- 适合追求高精度3D医学图像分割的研究者使用
3D医学图像分割虽因卷积神经网络（CNN）和视觉变换器（ViTs）取得显著进展，但难以兼顾长程依赖建模与计算效率。为此，我们提出UNetVL（U-Net Vision-LSTM），利用时序信息处理的新进展。该架构引入视觉LSTM（ViL）以提升可扩展性与记忆能力，并结合高效的切比雪夫柯尔莫哥洛夫-阿诺德网络（Chebyshev KAN），更有效地捕捉复杂且长程的依赖模式。我们在ACDC和AMOS2022（后挑战赛任务2）基准数据集上验证了该方法，相比近期最先进方法，尤其是其前身UNETR，平均Dice分数显著提升，分别达到7.3%和15.6%的增益。通过大量消融实验，全面分析了各组件的影响。代码已公开于https://github.com/tgrex6/UNETVL，便于进一步研究与应用。
原文摘要 · Abstract (English)
3D medical image segmentation has progressed considerably due to Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), yet these methods struggle to balance long-range dependency acquisition with computational efficiency. To address this challenge, we propose UNETVL (U-Net Vision-LSTM), a novel architecture that leverages recent advancements in temporal information processing. UNETVL incorporates Vision-LSTM (ViL) for improved scalability and memory functions, alongside an efficient Chebyshev Kolmogorov-Arnold Networks (KAN) to handle complex and long-range dependency patterns more effectively. We validated our method on the ACDC and AMOS2022 (post challenge Task 2) benchmark datasets, showing a significant improvement in mean Dice score compared to recent state-of-the-art approaches, especially over its predecessor, UNETR, with increases of 7.3% on ACDC and 15.6% on AMOS, respectively. Extensive ablation studies were conducted to demonstrate the impact of each component in UNETVL, providing a comprehensive understanding of its architecture. Our code is available at https://github.com/tgrex6/UNETVL, facilitating further research and applications in this domain.
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。