用数学模型提升医学图像少样本分割的准确率与可解释性
LMS-Net: A Learned Mumford-Shah Network For Few-Shot Medical Image Segmentation
- 基于学习的穆尔福德-沙赫模型，将原型与掩码更新交替优化
- 在三个公开数据集上达到领先性能，尤其擅长复杂结构分割
- 适合关注可解释性与小样本医学图像分割的研究者
少样本语义分割（FSS）方法在数据稀缺场景下展现出巨大潜力，尤其适用于医学图像分割任务。然而，现有大多数FSS架构缺乏足够可解释性，且未能充分融入语义区域的底层物理结构。为此，本文提出一种新型深度展开网络——学习型穆尔福德-沙赫网络（LMS-Net），用于少样本分割任务。受原型对比有效性和深层先验建模复杂空间结构能力的启发，我们以学习型穆尔福德-沙赫模型（LMS模型）为数学基础，将该模型重构为原型更新与掩码更新任务，提出一种交替优化算法高效求解。进一步地，将该算法的迭代步骤展开为对应的网络模块，构建出具有清晰可解释性的LMS-Net。在三个公开医学分割数据集上的全面实验验证了该方法的有效性，表现出优异的精度与鲁棒性，尤其在处理复杂结构和挑战性分割场景时表现突出。结果表明，LMS-Net有望推动医学影像中少样本分割的发展。代码将开源于：https://github.com/SDZhang01/LMSNet
原文摘要 · Abstract (English)
Few-shot semantic segmentation (FSS) methods have shown great promise in handling data-scarce scenarios, particularly in medical image segmentation tasks. However, most existing FSS architectures lack sufficient interpretability and fail to fully incorporate the underlying physical structures of semantic regions. To address these issues, in this paper, we propose a novel deep unfolding network, called the Learned Mumford-Shah Network (LMS-Net), for the FSS task. Specifically, motivated by the effectiveness of pixel-to-prototype comparison in prototypical FSS methods and the capability of deep priors to model complex spatial structures, we leverage our learned Mumford-Shah model (LMS model) as a mathematical foundation to integrate these insights into a unified framework. By reformulating the LMS model into prototype update and mask update tasks, we propose an alternating optimization algorithm to solve it efficiently. Further, the iterative steps of this algorithm are unfolded into corresponding network modules, resulting in LMS-Net with clear interpretability. Comprehensive experiments on three publicly available medical segmentation datasets verify the effectiveness of our method, demonstrating superior accuracy and robustness in handling complex structures and adapting to challenging segmentation scenarios. These results highlight the potential of LMS-Net to advance FSS in medical imaging applications. Our code will be available at: https://github.com/SDZhang01/LMSNet
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。