提出M³HL方法，提升半监督医学图像分割效果
M$^3$HL: Mutual Mask Mix with High-Low Level Feature Consistency for Semi-Supervised Medical Image Segmentation
- 动态可调掩码生成互补图像对，促进标签与无标签数据融合
- 在ACDC和LA数据集上达到当前最佳性能
- 适合医学图像分割研究者参考
受CutMix启发的数据增强方法在近期半监督医学图像分割任务中展现出巨大潜力。然而，这些方法通常以僵化方式应用CutMix，且对特征层面的一致性约束关注不足。本文提出一种新方法M³HL，包含两个关键组件：1）M³：受掩码图像建模（MIM）掩码策略启发的增强操作，通过动态可调掩码生成空间互补的图像对，实现标签与无标签图像间的协同训练，从而有效融合信息；2）HL：分层一致性正则化框架，强制无标签图像与混合图像在高层与低层特征上保持一致，使模型更准确捕捉判别性特征表示。该方法在广泛使用的医学图像分割基准如ACDC和LA数据集上取得当前最优性能。源代码已公开于https://github.com/PHPJava666/M3HL。
原文摘要 · Abstract (English)
Data augmentation methods inspired by CutMix have demonstrated significant potential in recent semi-supervised medical image segmentation tasks. However, these approaches often apply CutMix operations in a rigid and inflexible manner, while paying insufficient attention to feature-level consistency constraints. In this paper, we propose a novel method called Mutual Mask Mix with High-Low level feature consistency (M$^3$HL) to address the aforementioned challenges, which consists of two key components: 1) M$^3$: An enhanced data augmentation operation inspired by the masking strategy from Masked Image Modeling (MIM), which advances conventional CutMix through dynamically adjustable masks to generate spatially complementary image pairs for collaborative training, thereby enabling effective information fusion between labeled and unlabeled images. 2) HL: A hierarchical consistency regularization framework that enforces high-level and low-level feature consistency between unlabeled and mixed images, enabling the model to better capture discriminative feature representations.Our method achieves state-of-the-art performance on widely adopted medical image segmentation benchmarks including the ACDC and LA datasets. Source code is available at https://github.com/PHPJava666/M3HL
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。