Skip to content
Preprint

EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation

Aug 2026 · 0 citations · 1 references
Computer Science

TL;DR

This work proposes EA-LiteUNet, an edge-adaptive and computationally efficient U-Net variant specifically designed for boundary-sensitive medical image segmentation, and demonstrates that EA-LiteUNet consistently achieves superior boundary precision.

Abstract

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.

View source

Similar papers

Open access Sep 2026

GSCA-UNet: a gated spatial-channel attention U-net for accurate skin lesion segmentation

This work proposes GSCA-UNet (Gated Spatial-Channel Attention UNet), a novel segmentation architecture for skin lesions that consistently outperforms competitive baselines across multiple metrics and exhibits superior robustness on challenging cases with blurry borders, irregular shapes, and severe artifacts.

La-Zhen Zhou, Wen-Jie Ou, Xiu-Hua Chen et al. · 0 citations
Open access Aug 2026

MGA-UNet: A Frequency-Aware Multi-Scale Mamba U-Net for Medical Image Segmentation

MGA-UNet, a frequency-aware multi-scale encoder–decoder segmentation framework that integrates wavelet-based frequency decomposition with Mamba-based long-range dependency modelling, demonstrates that frequency-domain decomposition and state-space modelling can complement each other for accurate medical image segmentat...

Shuai-Kang Qiu, Xuan Wang, Kai-Le Su et al. · 0 citations
Conference Aug 2026

BE-Unet: a boundary-enhanced UNet for skin lesion segmentation

BE-Unet significantly outperforms state-of-the-art methods in segmentation accuracy and boundary delineation, with a parameters count limited to 38 KB and Giga-Operations Per Second (GFLOPs) limited to 0.1.

Xiaoman Huang, Zhenkun Lu · 0 citations
Open access Sep 2026

Mamba-EdgeNet: learnable edge-guided state space model for skin lesion segmentation

Evaluations on the official ISIC 2016 and ISIC 2018 splits, together with an internal evaluation using a nonstandard custom partition of ISIC 2017, indicate that the proposed architecture achieves competitive segmentation performance relative to recent representative models across multiple evaluation metrics.

Jia-Ming Xu, Qi Mao, Lei Qiu et al. · 0 citations
Open access Sep 2026

RDPA-UNet: Differential-Path Feature Learning and Multi-Scale Context Aggregation for Ultrasound Lesion Segmentation

RDPA-UNet provides robust lesion segmentation performance across heterogeneous ultrasound datasets while maintaining competitive boundary-localization accuracy, and demonstrates the effectiveness and complementarity of residual encoding, differential-path feature modeling, and multi-scale contextual aggregation.

Jia-Feng Jin, Hengsheng Zhang, Kun Wu · 0 citations
Sep 2026

Dual-Domain Structural Guidance with Grayscale-Enhanced Edge Learning for Robust Medical Image Segmentation.

A dual-domain structural guidance framework that integrates grayscale-guided edge features and graph-based multi-scale fusion to improve segmentation robustness and provides a reliable visual computing solution for clinical endoscopic image analysis.

Cheng-Xiang Zhang, Liang Jiang, Zhi-Chao Xu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.