用于体积医学图像分割的可学习权重初始化
Learnable Weight Initialization for Volumetric Medical Image Segmentation
AI总结：
本文提出一种面向混合体积医学图像分割模型的数据依赖可学习权重初始化方法，通过自监督目标学习医学体数据的上下文与结构信息，在多器官和肺癌分割任务上达到最先进性能。
摘要：
结合局部卷积与全局注意力优势的混合体积医学图像分割模型近期受到广泛关注。尽管现有混合方法主要关注架构改进，但多数仍采用传统的、与数据无关的权重初始化方案；这些方案忽视医学数据固有的体积特性，从而限制了模型性能。为解决该问题，我们提出一种可学习的权重初始化方法，利用可用的医学训练数据，通过所提出的自监督目标有效学习上下文与结构线索。该方法易于集成到任意混合模型中，并且不需要外部训练数据。在多器官和肺癌分割任务上的实验证明了本方法的有效性，并带来了最先进的分割性能。在多器官分割任务中，我们提出的数据依赖初始化方法与使用大规模数据集预训练的 Swin-UNETR 模型相比表现更优。源代码和模型可在 https://github.com/ShahinaKK/LWI-VMS 获取。
英文摘要：
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 proposed data-dependent initialization approach performs favorably as compared to the Swin-UNETR model pretrained using large-scale datasets on multi-organ segmentation task. Our source code and models are available at: https://github.com/ShahinaKK/LWI-VMS.
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。
