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. Our source code and models are available at: https://github.com/ShahinaKK/LWI-VMS.

翻译：混合体素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点，近年来受到广泛关注。然而，现有大多数混合方法主要关注架构改进，仍采用传统的数据无关权重初始化方案，因忽略了医学数据固有的体素本质特性而限制了其性能。针对这一问题，我们提出了一种可学习权重初始化方法，通过所设计的自监督目标有效利用可用医学训练数据来学习上下文及结构线索。该方法易于集成到任意混合模型中，且无需外部训练数据。在多器官和肺癌分割任务上的实验表明，该方法能够实现最先进的分割性能。我们的源代码和模型已开源：https://github.com/ShahinaKK/LWI-VMS。