浏览全部资源
扫码关注微信
收稿：2026-05-24，
修回：2026-08-12，
录用：2026-08-20，
网络首发：2026-08-20，
移动端阅览
目的
2
面向移动医疗与边缘部署场景下皮肤病灶分割对低运算量与高可靠性的双重需求，本文聚焦轻量网络在复杂皮肤镜图像中因浅层噪声传递、跨层融合失衡和边界约束不足而导致的结构感知与边界定位退化问题，提出一种选择性传递、自适应融合和聚焦边界监督的高效分割（selective transmission， adaptive fusion， and focused boundary supervision for efficient segmentation，SAFE）范式，并在轻量主干网络上实例化为轻量注意力特征融合与边界感知约束网络（lightweight attention-based feature fusion and boundary-aware constraints network，LEAF-UNet）。
方法
2
首先，在编码器与解码器间的跳跃连接路径入口引入轻量通道重标定机制（lightweight attention skip，LAS），利用通道统计信息对进入解码端前的浅层特征进行选择性筛选，从源头抑制毛发、标尺等背景噪声的传播；其次，在跨层特征聚合节点设计门控加权融合机制（gated weighted fusion，GWF），通过自适应权重分配机制动态协调低层纹理与高层语义的贡献度，以缓解固定融合策略下的语义细节失衡问题；最后，在训练过程中引入边界一致性监督（boundary consistency loss，BCL），其利用拉普拉斯算子提取预测掩膜与真实标注的轮廓响应，并通过显式几何一致性约束强化边界区域学习，改善低对比度和模糊边界条件下的病灶轮廓刻画能力。
结果
2
在国际皮肤影像协作组织（International Skin Imaging Collaboration，ISIC）2017和2018挑战赛数据集（ISIC2017、ISIC2018）以及PH
2
数据集上，LEAF-UNet以0.053 M参数量和0.075十亿浮点运算（giga floating-point operations，GFLOPs）分别取得89.50%、90.32%和94.83%的Dice系数，并较高效组增强U形网络（efficient group enhanced U-Net，EGE-UNet）显著降低第95百分位豪斯多夫距离，最大相对降幅约为30.28%。
结论
2
LEAF-UNet在保持极低模型复杂度的前提下，有效缓解了轻量模型在复杂场景下的结构感知退化问题，为资源受限环境下的皮肤病灶分割提供了具有参考价值的轻量化方案。本研究的数据集与源代码已发布于 Science Data Bank，访问链接为：
https：//doi.org/10.57760/sciencedb.j00240.00278
https://doi.org/10.57760/sciencedb.j00240.00278
。
Objective
2
Skin lesion segmentation is a fundamental task in computer-aided dermatological analysis， supporting lesion measurement， morphological assessment， risk evaluation， and subsequent clinical decision-making. With the growing demand for mobile healthcare， point-of-care screening， and edge intelligence， segmentation models are expected to achieve high accuracy and reliable boundary delineation under strict constraints on parameters， computation， and memory consumption. However， dermoscopic images often contain hair occlusion， ruler marks， illumination variation， color inhomogeneity， low contrast， and blurred lesion boundaries. These factors are particularly challenging for lightweight networks， whose limited representational capacity makes them vulnerable to shallow-feature noise propagation， imbalanced cross-layer feature fusion， and insufficient boundary supervision. Existing lightweight segmentation methods usually emphasize backbone compression or a single enhancement module. They rarely consider how noisy shallow features， mismatched semantic-detail fusion， and weak contour constraints may form a continuous degradation process. To address this issue， this study proposes a lightweight skin lesion segmentation framework based on selective transmission， adaptive fusion， and focused boundary supervision for efficient segmentation （SAFE）， which is instantiated as LEAF-UNet on a lightweight encoder-decoder backbone.
Methods
2
The proposed method follows a coordinated “transmission-fusion-supervision” design. Instead of increasing network depth or introducing computationally expensive global modeling modules， it performs targeted refinement at three critical information-flow stages in a lightweight U-shaped segmentation architecture. First， a lightweight attention skip （LAS） mechanism is inserted at the entrance of each skip connection between the encoder and decoder. In conventional encoder-decoder networks， shallow features preserve fine spatial details but may also transmit background interference directly to the decoder. This issue is prominent in dermoscopic images， where hair， ruler marks， specular reflections， and texture variations may be captured as strong shallow responses. LAS employs channel-wise global statistical information to estimate the relevance of each channel before shallow features are delivered to the decoder. Through lightweight channel recalibration， informative channels associated with lesion structures are retained， while redundant or noise-dominated channels are suppressed. Therefore， the decoder receives more discriminative shallow representations without changing the spatial resolution of the feature maps or introducing substantial additional computation. Second， a gated weighted fusion （GWF） mechanism is designed for cross-layer feature aggregation. Traditional feature fusion strategies， such as direct concatenation or element-wise addition， assume that shallow texture features and deep semantic features make fixed contributions across different images and spatial locations. This assumption is unsuitable for skin lesions with diverse scales， irregular shapes， low contrast， and ambiguous boundaries. GWF first aligns the shallow and deep features in spatial size and channel dimension. It then generates complementary， normalized gating weights to adaptively determine the contributions of low-level details and high-level semantic information at each spatial location. In regions with strong background texture or irrelevant local structures， the model can increase the contribution of deep semantic features to suppress false responses. In boundary regions or areas with subtle lesion details， the model can preserve more shallow information to avoid detail loss. This adaptive fusion strategy improves the balance between semantic consistency and boundary detail recovery. Third， a boundary consistency loss （BCL） is introduced during training to supplement region-based supervision. Binary cross-entropy loss and Dice loss mainly optimize pixel-wise classification and region overlap， but they may not directly constrain geometric consistency between predicted boundaries and ground-truth contours. BCL uses a fixed Laplacian operator to extract contour responses from the predicted probability map and the ground-truth mask. The difference between these contour responses is incorporated into the training objective as an explicit boundary constraint. This mechanism encourages the network to focus on boundary transition regions and improves contour delineation under low-contrast and blurred-boundary conditions. Importantly， BCL is used only during training. It introduces no additional inference branch， learnable parameters， post-processing operation， or deployment-time computational burden.The three components are designed to be complementary. LAS reduces the propagation of irrelevant shallow noise before feature fusion； GWF adaptively integrates filtered shallow details with deep semantic features； and BCL constrains the final prediction from the perspective of boundary geometry. Consequently， LEAF-UNet improves segmentation reliability through a lightweight closed-loop design rather than through a substantial increase in model capacity.
Results
2
Experiments were conducted on the International Skin Imaging Collaboration 2017 and 2018 challenge datasets （ISIC2017 and ISIC2018） and the PH² dermoscopic image dataset. The performance of LEAF-UNet was evaluated using the mean intersection over union， Dice similarity coefficient， and 95th-percentile Hausdorff distance （HD95）. Model efficiency was assessed using parameter count and giga floating-point operations （GFLOPs）. LEAF-UNet contains only 0.053 × 10⁶ parameters and requires 0.075 GFLOPs， demonstrating its suitability for computation-constrained deployment scenarios.Despite its extremely small model size， LEAF-UNet achieved Dice coefficients of 89.50%， 90.32%， and 94.83% on ISIC2017， ISIC2018， and PH²， respectively. Its corresponding mean intersection over union values were 81.26%， 81.76%， and 90.45%. These results demonstrate that the proposed network maintains strong region-overlap performance across datasets with different sample scales， lesion characteristics， and imaging conditions. In comparison with the efficient group-enhanced U-Net （EGE-UNet）， which is used as the lightweight backbone baseline， LEAF-UNet improves both overlap-based and boundary-sensitive performance while retaining a comparable parameter count. In particular， the proposed method substantially reduces HD95， with a maximum relative reduction of approximately 30.28%. The improvement is especially evident on the PH² dataset， where LEAF-UNet obtains an HD95 of 9.51 pixels， indicating more accurate and stable lesion contour localization.Ablation experiments further verify the contribution of each component. Introducing LAS alone improves robustness against shallow background interference by filtering skip-connection features before decoding. GWF alone improves the coordination between detailed texture information and high-level semantic representations. BCL alone enhances contour learning by imposing a direct geometric consistency constraint. When the three components are combined， the complete LEAF-UNet obtains the best overall performance， confirming that selective feature transmission， adaptive cross-layer fusion， and training-time boundary supervision are mutually beneficial. Additional analyses of hyperparameter sensitivity， neighboring-module replacement， and per-case HD95 distributions show that the proposed design provides stable gains without relying on heavy attention modules， complex post-processing， or additional inference-stage branches.
Conclusion
2
LEAF-UNet is a lightweight skin lesion segmentation network that addresses structural perception degradation in resource-constrained settings through coordinated feature transmission， feature fusion， and boundary supervision. The LAS mechanism suppresses shallow noise propagation， GWF adaptively balances low-level details and high-level semantics， and BCL improves boundary consistency without increasing inference complexity. Experimental results on ISIC2017， ISIC2018， and PH² demonstrate that LEAF-UNet achieves competitive segmentation accuracy and substantially improved boundary localization with only 0.053 × 10⁶ parameters and 0.075 GFLOPs. The proposed framework provides an effective and deployment-friendly solution for skin lesion segmentation in mobile healthcare and edge computing environments. The dataset and source code developed in this study have been released through Science Data Bank and are available at：
https：//doi.org/10.57760/sciencedb.j00240.00278
https://doi.org/10.57760/sciencedb.j00240.00278
.
Asgari Taghanaki S ， Abhishek K ， Cohen J P ， Cohen-Adad J and Hamarneh G . 2021 . Deep semantic segmentation of natural and medical images： a review . Artificial Intelligence Review ， 54 （ 1 ）： 137 - 178 ［ DOI： 10.1007/s10462-020-09854-1 http://dx.doi.org/10.1007/s10462-020-09854-1 ］.
Cao H ， Wang Y ， Chen J ， Jiang D ， Zhang X ， Tian Q ， et al . 2022 . Swin-Unet： Unet-like pure transformer for medical image segmentation // Computer Vision–ECCV 2022 Workshops . Cham ： Springer： 205 - 218 ［DOI： 10.1007/978-3-031-25066-8_9］.
Codella N C F ， Gutman D ， Celebi M E ， Helba B ， Marchetti M A ， Dusza S W ， et al . 2017 . Skin lesion analysis toward melanoma detection： a challenge at the 2017 International Symposium on Biomedical Imaging （ISBI）， hosted by the International Skin Imaging Collaboration （ISIC） ［EB/OL］. ［ 2026-08-11 ］. https://arxiv.org/abs/1710.05006 https://arxiv.org/abs/1710.05006 ［ DOI： 10.48550/arXiv.1710.05006 http://dx.doi.org/10.48550/arXiv.1710.05006 ］.
Codella N ， Rotemberg V ， Tschandl P ， Celebi M E ， Dusza S ， Gutman D ， et al . 2019 . Skin lesion analysis toward melanoma detection 2018： a challenge hosted by the International Skin Imaging Collaboration （ISIC） ［EB/OL］. ［ 2026-08-11 ］. https://arxiv.org/abs/1902.03368 https://arxiv.org/abs/1902.03368 ［ DOI： 10.48550/arXiv.1902.03368 http://dx.doi.org/10.48550/arXiv.1902.03368 ］.
Hu G ， Zhu W ， Liao X and Li Q . 2025 . WA-NET： enhanced boundary-aware segmentation of skin lesions via frequency-spatial feature fusion and attention-guided edge refinement . Scientific Reports ， 15 ： 41598 ［DOI： 10.1038/s41598-025-25583-3］ .
Huang X ， Ma Y ， Mei X ， Wu Z ， Sun M and She Q . 2025 . Lesion boundary detection for skin lesion segmentation based on boundary sensing and CNN-transformer fusion networks . Artificial Intelligence in Medicine ， 167 ： 103190 ［DOI： 10.1016/j.artmed.2025.103190］ .
Kervadec H ， Bouchtiba J ， Desrosiers C ， Granger E ， Dolz J and Ben Ayed I . 2019 . Boundary loss for highly unbalanced segmentation // Proceedings of the 2nd International Conference on Medical Imaging with Deep Learning . London ： PMLR ， 102 ： 285 - 296 .
Li H ， Liu J J and Xiao L . 2024 . Dual-encoder global-local cross-attention network for medical image segmentation . Journal of Image and Graphics ， 29 （ 11 ）： 3462 - 3475
李赫 ， 刘建军 ， 肖亮 . 2024 . 融合交叉注意力与双编码器的医学图像分割 . 中国图象图形学报 ， 29 （ 11 ）： 3462 - 3475 ［ DOI： 10.11834/jig.230705 http://dx.doi.org/10.11834/jig.230705 ］.
Liu S J and Tong M J . 2026 . Swin-EdgeNet： medical image segmentation with multi-scale edge enhancement based on transformer ［J/OL］. Journal of Image and Graphics， XXXX： 1 - 14 刘善洁， 童孟军. 2026 . Swin-EdgeNet：基于Transformer的多尺度边缘增强医学图像分割模型 ［J/OL］. 中国图象图形学报 ， XXXX： 1- 14 ［DOI： 10.11834/jig.250592］.
Liu X ， Gao P ， Yu T ， Wang F and Yuan R Y . 2025 . CSWin-UNet： transformer UNet with cross-shaped windows for medical image segmentation . Information Fusion ， 113 ： 102634 ［DOI： 10.1016/j.inffus.2024.102634］ .
Mendonça T ， Ferreira P M ， Marques J S ， Marcal A R S and Rozeira J . 2013 . PH²： a dermoscopic image database for research and benchmarking // 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society （EMBC） . Osaka ： IEEE： 5437 - 5440 ［DOI： 10.1109/EMBC.2013.6610779］.
Mirikharaji Z ， Abhishek K ， Bissoto A ， Barata C ， Avila S ， Valle E ， et al . 2023 . A survey on deep learning for skin lesion segmentation . Medical Image Analysis ， 88 ： 102863 ［DOI： 10.1016/j.media.2023.102863］ .
Munia A A ， Abdar M ， Hasan M ， Jalali M S ， Banerjee B ， Khosravi A ， et al . 2025 . Attention-guided hierarchical fusion U-Net for uncertainty-driven medical image segmentation . Information Fusion ， 115 ： 102719 ［DOI： 10.1016/j.inffus.2024.102719］ .
Oktay O ， Schlemper J ， Le Folgoc L ， Lee M J ， Heinrich M P ， Misawa K ， et al . 2018 . Attention U-Net： learning where to look for the pancreas ［EB/OL］. ［ 2026-08-11 ］. https://arxiv.org/abs/1804.03999 https://arxiv.org/abs/1804.03999 ［ DOI： 10.48550/arXiv.1804.03999 http://dx.doi.org/10.48550/arXiv.1804.03999 ］.
Qiu P ， Yang J ， Kumar S ， Ghosh S S and Sotiras A . 2026 . AgileFormer： spatially agile and scalable transformer for medical image segmentation . Biomedical Signal Processing and Control ， 112 ： 108842 ［DOI： 10.1016/j.bspc.2025.108842］ .
Qureshi I ， Yan J ， Abbas Q ， Shaheed K ， Riaz A B ， Wahid A ， et al . 2023 . Medical image segmentation using deep semantic-based methods： a review of techniques， applications and emerging trends . Information Fusion ， 90 ： 316 - 352 ［ DOI： 10.1016/j.inffus.2022.09.031 http://dx.doi.org/10.1016/j.inffus.2022.09.031 ］.
Ronneberger O ， Fischer P and Brox T . 2015 . U-Net： convolutional networks for biomedical image segmentation // Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015 . Cham ： Springer： 234 - 241 ［DOI： 10.1007/978-3-319-24574-4_28］.
Ruan J ， Xiang S ， Xie M ， Liu T and Fu Y . 2022 . MALUNet： a multi-attention and light-weight UNet for skin lesion segmentation // 2022 IEEE International Conference on Bioinformatics and Biomedicine （BIBM） . Las Vegas ： IEEE： 1150 - 1156 ［DOI： 10.1109/BIBM55620.2022.9995040］.
Ruan J ， Xie M ， Gao J ， Liu T and Fu Y . 2023 . EGE-UNet： an efficient group enhanced UNet for skin lesion segmentation // Medical Image Computing and Computer Assisted Intervention–MICCAI 2023 . Cham ： Springer： 481 - 490 ［DOI： 10.1007/978-3-031-43901-8_46］.
Shaker A ， Maaz M ， Rasheed H ， Khan S ， Yang M H and Khan F S . 2024 . UNETR++： delving into efficient and accurate 3D medical image segmentation . IEEE Transactions on Medical Imaging ， 43 （ 9 ）： 3377 - 3390 ［ DOI： 10.1109/TMI.2024.3398728 http://dx.doi.org/10.1109/TMI.2024.3398728 ］.
Shi J ， Wang T T ， Zhu Z Q ， Zhao M F ， Wang B X and An H . 2025 . Deep learning-based medical image segmentation methods . Journal of Image and Graphics ， 30 （ 6 ）： 2161 - 2186
石军 ， 王天同 ， 朱子琦 ， 赵敏帆 ， 王炳勋 ， 安虹 . 2025 . 基于深度学习的医学图像分割方法综述 . 中国图象图形学报 ， 30 （ 6 ）： 2161 - 2186 ［ DOI： 10.11834/jig.240467 http://dx.doi.org/10.11834/jig.240467 ］.
Valanarasu J M J and Patel V M . 2022 . UNeXt： MLP-based rapid medical image segmentation network // Medical Image Computing and Computer Assisted Intervention–MICCAI 2022 . Cham ： Springer： 23 - 33 ［DOI： 10.1007/978-3-031-16443-9_3］.
Wang Q ， Wu B ， Zhu P ， Li P ， Zuo W and Hu Q . 2020 . ECA-Net： efficient channel attention for deep convolutional neural networks // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR） . Seattle ： IEEE： 11534 - 11542 ［DOI： 10.1109/CVPR42600.2020.01155］.
Wang R ， Lei T ， Cui R ， Zhang B ， Meng H and Nandi A K . 2022 . Medical image segmentation using deep learning： a survey . IET Image Processing ， 16 （ 5 ）： 1243 - 1267 ［ DOI： 10.1049/ipr2.12419 http://dx.doi.org/10.1049/ipr2.12419 ］.
Wu R ， Liu Y ， Ning G ， Liang P and Chang Q . 2025 . UltraLight VM-UNet： parallel Vision Mamba significantly reduces parameters for skin lesion segmentation . Patterns ， 6 （ 11 ）： 101298 ［DOI： 10.1016/j.patter.2025.101298］ .
Xu J and Tong L . 2024 . LB-UNet： a lightweight boundary-assisted UNet for skin lesion segmentation // Medical Image Computing and Computer Assisted Intervention–MICCAI 2024 . Cham ： Springer： 361 - 371 ［DOI： 10.1007/978-3-031-72114-4_35］.
Zhang D ， Huang H ， Ma Y ， Huang B C and Lu W P . 2024 . Prostate MR image segmentation network with edge information enhancement . Journal of Image and Graphics ， 29 （ 3 ）： 755 - 767
张蝶 ， 黄慧 ， 马燕 ， 黄丙仓 ， 陆炜平 . 2024 . 基于边缘信息增强的前列腺MR图像分割网络 . 中国图象图形学报 ， 29 （ 3 ）： 755 - 767 ［ DOI： 10.11834/jig.230338 http://dx.doi.org/10.11834/jig.230338 ］.
Zhang H ， Qiu D W ， Feng Y B and Liu J . 2022 . Improved U-Net models and its applications in medical image segmentation： a review . Laser & Optoelectronics Progress ， 59 （ 2 ）： 55 - 71
张欢 ， 仇大伟 ， 冯毅博 ， 刘静 . 2022 . U-Net模型改进及其在医学图像分割上的研究综述 . 激光与光电子学进展 ， 59 （ 2 ）： 55 - 71 ［ DOI： 10.3788/LOP202259.0200005 http://dx.doi.org/10.3788/LOP202259.0200005 ］.
Zhang M ， Yu Y ， Jin S ， Gu L ， Ling T and Tao X . 2024 . VM-UNET-V2： rethinking Vision Mamba UNet for medical image segmentation // Bioinformatics Research and Applications： 20th International Symposium ， ISBRA 2024. Singapore ： Springer： 335 - 346 ［DOI： 10.1007/978-981-97-5128-0_27］.
Zhou Z ， Siddiquee M M R ， Tajbakhsh N and Liang J . 2018 . UNet++： a nested U-Net architecture for medical image segmentation // Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support . Cham ： Springer： 3 - 11 ［DOI： 10.1007/978-3-030-00889-5_1］.
相关作者
相关机构
京公网安备11010802024621
