Differential-UMamba：在有限数据场景下重新思考肿瘤分割
Differential-UMamba: Rethinking Tumor Segmentation Under Limited Data Scenarios
AI总结：
本文提出Diff-UMamba架构，结合UNet与mamba机制以建模长距离依赖，通过噪声减少模块抑制噪声激活，提升分割准确性与鲁棒性，在低数据场景下实现1-3%的性能提升。
摘要：
在数据稀缺场景中，深度学习模型常过度拟合噪声和无关模式，限制其对未见样本的泛化能力。为解决这些挑战，我们引入Diff-UMamba，一种结合UNet框架与mamba机制的新架构，以建模长距离依赖。Diff-UMamba的核心是一个噪声减少模块，采用信号差分策略以抑制编码器内的噪声或无关激活。这促使模型过滤掉虚假特征，增强任务相关表示，从而提高对临床重要区域的关注。因此，该架构在低数据设置中实现了改进的分割准确性和鲁棒性。Diff-UMamba在多个公共数据集上进行评估，包括医学分割decathalon数据集（肺和胰腺）和AIIB23，展示了在各种分割任务中相对于基线方法的持续性能提升。为进一步评估在有限数据条件下的性能，还在BraTS-21数据集上进行了额外实验，通过变化可用训练样本的比例进行测试。该方法还在一个小的内部非小细胞肺癌数据集上进行了验证，用于锥束CT中gross tumor volume的分割，其中在基线方法上实现了4-5%的提升。
英文摘要：
In data-scarce scenarios, deep learning models often overfit to noise and irrelevant patterns, which limits their ability to generalize to unseen samples. To address these challenges in medical image segmentation, we introduce Diff-UMamba, a novel architecture that combines the UNet framework with the mamba mechanism to model long-range dependencies. At the heart of Diff-UMamba is a noise reduction module, which employs a signal differencing strategy to suppress noisy or irrelevant activations within the encoder. This encourages the model to filter out spurious features and enhance task-relevant representations, thereby improving its focus on clinically significant regions. As a result, the architecture achieves improved segmentation accuracy and robustness, particularly in low-data settings. Diff-UMamba is evaluated on multiple public datasets, including medical segmentation decathalon dataset (lung and pancreas) and AIIB23, demonstrating consistent performance gains of 1-3% over baseline methods in various segmentation tasks. To further assess performance under limited data conditions, additional experiments are conducted on the BraTS-21 dataset by varying the proportion of available training samples. The approach is also validated on a small internal non-small cell lung cancer dataset for the segmentation of gross tumor volume in cone beam CT, where it achieves a 4-5% improvement over baseline.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
