轻量级模型精准分割皮肤病变，兼顾速度与细节。
MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation
- 将Mamba状态空间模型融入U-Net，通过自适应融合增强特征表达。
- 在多个数据集上平均交并比达87.12%，参数减少93.6%，计算量降97.6%。
- 适用于医疗图像分割场景，尤其适合资源受限的临床部署。
近期分割模型通过大幅压缩参数和计算量展现了高效性，但往往难以准确勾勒细小病变边界与纹理，影响早期皮肤癌诊断。本文提出MambaLiteUNet，一种紧凑且鲁棒的分割框架，将Mamba状态空间建模引入U-Net架构，并设计三个核心模块：自适应多分支Mamba特征融合（AMF）、局部-全局特征混合（LGFM）与跨门控注意力（CGA），以强化局部-全局特征交互、保留空间细节并提升跳跃连接质量。该模型在ISIC2017、ISIC2018、HAM10000和PH2数据集上平均交并比（IoU）达87.12%，平均骰子系数（Dice）为93.09%，优于现有先进模型。相比U-Net，IoU提升7.72点，Dice提升4.61点，同时参数减少93.6%，GFLOPs降低97.6%。在六种未见病变类别的域泛化测试中，取得77.61% IoU与87.23% Dice，表现最优。实验表明，MambaLiteUNet在精度与效率间实现良好平衡，具备临床实用价值。代码已开源。
原文摘要 · Abstract (English)
Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, these models often struggle to accurately delineate fine lesion boundaries and texture patterns essential for early skin cancer diagnosis and treatment planning. In this paper, we propose MambaLiteUNet, a compact yet robust segmentation framework that integrates Mamba state space modeling into a U-Net architecture, along with three key modules: Adaptive Multi-Branch Mamba Feature Fusion (AMF), Local-Global Feature Mixing (LGFM), and Cross-Gated Attention (CGA). These modules are designed to enhance local-global feature interaction, preserve spatial details, and improve the quality of skip connections. MambaLiteUNet achieves an average IoU of 87.12% and average Dice score of 93.09% across ISIC2017, ISIC2018, HAM10000, and PH2 benchmarks, outperforming state-of-the-art models. Compared to U-Net, our model improves average IoU and Dice by 7.72 and 4.61 points, respectively, while reducing parameters by 93.6% and GFLOPs by 97.6%. Additionally, in domain generalization with six unseen lesion categories, MambaLiteUNet achieves 77.61% IoU and 87.23% Dice, performing best among all evaluated models. Our extensive experiments demonstrate that MambaLiteUNet achieves a strong balance between accuracy and efficiency, making it a competitive and practical solution for dermatological image segmentation. Our code is publicly available at: https://github.com/maklachur/MambaLiteUNet.
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。