Hybrid volumetric medical image segmentation models, combining the advantages of local convolution and global attention, have recently received considerable attention. While mainly focusing on architectural modifications, most existing hybrid approaches still use conventional data-independent weight initialization schemes which restrict their performance due to ignoring the inherent volumetric nature of the medical data. To address this issue, we propose a learnable weight initialization approach that utilizes the available medical training data to effectively learn the contextual and structural cues via the proposed self-supervised objectives. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach, leading to state-of-the-art segmentation performance.

翻译：混合型体积医学图像分割模型结合了局部卷积与全局注意力机制的优势，近期受到了广泛关注。然而，现有大多数混合方法仍主要关注架构改进，其采用的常规数据无关权重初始化方案因忽略医学数据固有的体积特性而限制了性能。为解决此问题，我们提出一种可学习的权重初始化方法，通过设计的自监督目标函数有效利用现有医学训练数据学习上下文与结构线索。该方法易于集成至任何混合模型，且无需外部训练数据。在多器官与肺癌分割任务上的实验表明，本方法能有效提升分割性能，达到当前最优水平。