EA-LiteUNet：用于边界敏感皮肤镜图像分割的边缘自适应且资源高效的U-Net
EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation
AI总结：
本文针对皮肤镜图像分割的边界描绘难题，提出边缘自适应且资源高效的EA-LiteUNet，通过三类核心机制实现高精度边界分割，在公开数据集上以超轻量配置取得优异性能。
AI中文摘要：
在皮肤镜图像分割中，精确的边界描绘仍是一个持续存在的挑战，因为病变边缘模糊、纹理异质且背景存在复杂伪影。从信号处理角度来看，病变边界代表易受混叠、噪声放大和信息丢失影响的高频分量，因此传统卷积架构中的重复下采样和特征转换常会导致边界表示严重退化。为解决这些局限，本文提出EA-LiteUNet，一种专为边界敏感医学图像分割设计的边缘自适应且计算高效的U-Net变体。该架构整合了三个核心机制：（1）边界感知表示学习，用于抑制混叠并保留高频结构细节；（2）注意力引导的特征调制，用于选择性增强多尺度特征中与边界相关的响应；（3）资源自适应推理策略，用于动态平衡分割精度与计算效率。在三个公开皮肤镜数据集上的广泛评估表明，EA-LiteUNet始终实现更优的边界精度。具体而言，在ISIC 2018数据集上，该方法将95%豪斯多夫距离（HD95）显著降低至12.89像素，同时保持92.08%的稳健戴斯系数（Dice score）。值得注意的是，这一优异性能是在仅0.29M参数、1.17 GFLOPs的超轻量配置下实现的。 ablation研究进一步验证了这些组件的互补效应，确认它们对提升边界保真度和稳定优化的贡献。
英文摘要：
Accurate boundary delineation remains a persistent challenge in dermoscopic image segmentation because of blurred lesion margins, heterogeneous textures, and complex background artifacts. From a signal-processing perspective, lesion boundaries represent high-frequency components that are highly susceptible to aliasing, noise amplification, and information loss. Consequently, repeated downsampling and feature transformations in conventional convolutional architectures often lead to severely degraded boundary representations. To address these limitations, we propose EA-LiteUNet, an edge-adaptive and computationally efficient U-Net variant specifically designed for boundary-sensitive medical image segmentation. The architecture integrates three core mechanisms: (1) boundary-aware representation learning to suppress aliasing and preserve high-frequency structural details; (2) attention-guided feature modulation to selectively enhance boundary-relevant responses across multi-scale features; and (3) a resource-adaptive inference strategy to dynamically balance segmentation accuracy and computational efficiency. Extensive evaluations across three public dermoscopic datasets demonstrate that EA-LiteUNet consistently achieves superior boundary precision. Specifically, on the ISIC 2018 dataset, the method significantly reduces the 95% Hausdorff Distance (HD95) to 12.89 pixels while maintaining a robust Dice score of 92.08%. Notably, this strong performance is achieved with an ultralightweight configuration of merely 0.29M parameters and 1.17 GFLOPs. Ablation studies further validate the complementary effects of these components, confirming their contribution to enhanced boundary fidelity and stable optimization.
