UltraLBM-UNet：轻量双向Mamba模型用于皮肤病变分割
UltraLBM-UNet: Ultralight Bidirectional Mamba-based Model for Skin Lesion Segmentation
AI总结：
UltraLBM-UNet通过整合双向Mamba机制和多分支局部特征感知，实现轻量级皮肤病变分割，具有高效计算和高分割精度。
摘要：
皮肤病变分割是皮肤病学中指导临床决策的关键步骤。然而，现有方法在准确、鲁棒和资源高效分析方面存在局限，包括性能低和计算复杂度高。为解决这些问题，我们提出了UltraLBM-UNet，一种轻量化的U-Net变体，集成了双向Mamba基于的全局建模机制与多分支局部特征感知。所提出的架构整合了高效的局部特征注入与双向状态空间建模，使模型在保持计算紧凑性的同时，能够在空间维度上实现更丰富的上下文交互。在ISIC 2017、ISIC 2018和PH2数据集上的大量实验表明，我们的模型在分割准确性方面始终处于领先地位，仅使用0.034M参数和0.060 GFLOPs，就优于现有的轻量级和Mamba方法。此外，我们引入了一种混合知识蒸馏策略来训练一个超紧凑的学生模型，其中蒸馏后的UltraLBM-UNet-T模型仅使用0.011M参数和0.019 GFLOPs，实现了具有竞争力的分割性能。这些结果突显了UltraLBM-UNet在点即服务部署中的适用性，其中准确且鲁棒的病变分析至关重要。源代码可在https://github.com/LinLinLin-X/UltraLBM-UNet上公开获取。
英文摘要：
Skin lesion segmentation is a crucial step in dermatology for guiding clinical decision-making. However, existing methods for accurate, robust, and resource-efficient lesion analysis have limitations, including low performance and high computational complexity. To address these limitations, we propose UltraLBM-UNet, a lightweight U-Net variant that integrates a bidirectional Mamba-based global modeling mechanism with multi-branch local feature perception. The proposed architecture integrates efficient local feature injection with bidirectional state-space modeling, enabling richer contextual interaction across spatial dimensions while maintaining computational compactness suitable for point-of-care deployment. Extensive experiments on the ISIC 2017, ISIC 2018, and PH2 datasets demonstrate that our model consistently achieves state-of-the-art segmentation accuracy, outperforming existing lightweight and Mamba counterparts with only 0.034M parameters and 0.060 GFLOPs. In addition, we introduce a hybrid knowledge distillation strategy to train an ultra-compact student model, where the distilled variant UltraLBM-UNet-T, with only 0.011M parameters and 0.019 GFLOPs, achieves competitive segmentation performance. These results highlight the suitability of UltraLBM-UNet for point-of-care deployment, where accurate and robust lesion analyses are essential. The source code is publicly available at https://github.com/LinLinLin-X/UltraLBM-UNet.
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。
