Feature Learning and Boundary Guidance for Skin Lesion Image Segmentation Network

doi:10.19678/j.issn.1000-3428.0070434

Abstract

Abstract:

Skin lesion images significantly affect the accuracy of segmentation algorithms because of characteristics such as blurred lesion boundaries, large variations in size, and irregular shapes. To address this issue, a skin lesion image segmentation network that combines feature learning and boundary guidance is proposed. First, a dual feature encoding module based on Convolutional Neural Networks (CNN) and a Transformer is constructed to learn the global-local features of skin lesion images. Subsequently, expert-annotated ground truth supervised learning is adopted to guide the generation of the skin lesion boundary windows and enhance the boundary features of the lesion. Finally, by introducing a boundary-guided decoding mechanism, the learned global-local features and boundary-enhanced features are fused to perform skin lesion image segmentation, optimizing the boundary clarity and overall accuracy of the segmentation results. Experimental results on the ISIC 2018 and ISIC 2016 datasets show that the proposed method achieves improvements of 2.88, 1.25, and 0.27 percentage points in Intersection over Union (IoU), specificity, and accuracy, respectively, compared with CTO on the ISIC 2018 dataset. For the ISIC 2016 dataset, the Dice coefficient and IoU are improved by 1.66 and 6.02 percentage points, respectively, achieving optimal results across all evaluation metrics. The proposed segmentation network exhibits excellent performance in segmentation tasks with complex backgrounds and blurred boundaries, accurately segmenting lesion regions and effectively handling boundary blurring issues in complex backgrounds, thereby providing a high-precision solution for skin lesion image segmentation.

Key words: skin lesion image segmentation, feature encoding, feature learning, boundary guiding, boundary enhancement

摘要：

皮肤病变图像因病变区域边界模糊、尺寸变化大、形状不规则等特性, 显著影响分割算法的准确性。针对该问题, 提出一种结合特征学习和边界引导的皮肤病变图像分割网络。首先, 构建基于卷积神经网络(CNN)和Transformer的双重特征编码模块, 学习皮肤病变图像的全局-局部特征; 然后, 采用专家标注的真值监督学习指导生成皮肤病变边界窗口, 对病变区域进行边界特征增强; 最后, 通过引入边界引导解码机制, 融合学习到的全局-局部特征和边界增强特征, 进行皮肤病变图像分割, 优化分割结果的边界清晰度和整体精度。在ISIC 2018和ISIC 2016数据集上的实验结果表明, 该方法在ISIC 2018数据集上的交并比(IoU)、特异性和准确率相比CTO分别提高2.88、1.25和0.27百分点, 在ISIC 2016数据集上, Dice系数和IoU分别提高1.66和6.02百分点, 并在所有评估指标上均取得最优结果。所提分割网络在复杂背景及模糊边界病变的分割任务中表现出卓越性能, 不仅能够精准分割病变区域, 还能有效处理复杂背景下的边界模糊问题, 为皮肤病变图像分割提供了一种高精度的解决方案。

关键词: 皮肤病变图像分割, 特征编码, 特征学习, 边界引导, 边界增强

LIU Menghan, LIU Li, FU Xiaodong, LIU Lijun, PENG Wei. Feature Learning and Boundary Guidance for Skin Lesion Image Segmentation Network[J]. Computer Engineering, 2026, 52(7): 243-254.

刘梦寒, 刘骊, 付晓东, 刘利军, 彭玮. 特征学习和边界引导的皮肤病变图像分割网络[J]. 计算机工程, 2026, 52(7): 243-254.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070434

https://www.ecice06.com/EN/Y2026/V52/I7/243

Figures/Tables 8

References 37

1	SIEGEL R L , GIAQUINTO A N , JEMAL A . Cancer statistics, 2024. CA: A Cancer Journal for Clinicians, 2024, 74(1): 12- 49. doi: 10.3322/caac.21820
2	GE Z Y, DEMYANOV S, CHAKRAVORTY R, et al. Skin disease recognition using deep saliency features and multimodal learning of dermoscopy and clinical images[EB/OL]. [2024-08-05]. https://link.springer.com/chapter/10.1007/978-3-319-66179-7_29.
3	ALGARIN Y A , MCCULLUM C , PATEL V A . 33256 skin cancer screening practices among dermatologists: a survey study. Journal of the American Academy of Dermatology, 2022, 87(3): AB203.
4	赵宏, 王枭. 基于Swin-Transformer的黑色素瘤图像病灶分割研究. 计算机工程, 2024, 50(8): 249- 258. doi: 10.19678/j.issn.1000-3428.0068267
	ZHAO H , WANG X . Study on lesion segmentation of melanoma images based on Swin-Transformer. Computer Engineering, 2024, 50(8): 249- 258. doi: 10.19678/j.issn.1000-3428.0068267
5	SUN Y H , DAI D W , ZHANG Q N , et al. MSCA-Net: multi-scale contextual attention network for skin lesion segmentation. Pattern Recognition, 2023, 139, 109524. doi: 10.1016/j.patcog.2023.109524
6	CELEBI M E, IYATOMI H, SCHAEFER G, et al. Localization of lesions in dermoscopy images using ensembles of thresholding methods[EB/OL]. [2024-08-05]. https://link.springer.com/chapter/10.1007/978-3-540-92957-4_95.
7	GOMEZ D D , BUTAKOFF C , ERSBOLL B K , et al. Independent histogram pursuit for segmentation of skin lesions. IEEE Transactions on Biomedical Engineering, 2008, 55(1): 157- 161. doi: 10.1109/TBME.2007.910651
8	RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[EB/OL]. [2024-08-05]. https://arxiv.org/abs/1505.04597.
9	HUANG H M, LIN L F, TONG R F, et al. UNet 3+: a full-scale connected UNet for medical image segmentation[C]// Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2020: 1055-1059.
10	CHEN L C , PAPANDREOU G , KOKKINOS I , et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834- 848. doi: 10.1109/TPAMI.2017.2699184
11	李大湘, 杨福杰, 刘颖, 等. 融入交叉注意力编码的皮肤病变分割网络. 光学精密工程, 2024, 32(4): 609- 621.
	LI D X , YANG F J , LIU Y , et al. Skin lesion segmentation network with cross-attention coding. Optics and Precision Engineering, 2024, 32(4): 609- 621.
12	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL]. [2024-08-05]. https://arxiv.org/abs/2010.11929.
13	CHEN F, WANG J C, MAGNIER B, et al. G2LL: global-to-local self-supervised learning for label-efficient transformer-based skin lesion segmentation in dermoscopy images[C]// Proceedings of the 20th IEEE International Symposium on Biomedical Imaging (ISBI). Washington D.C., USA: IEEE Press, 2023: 1-5.
14	XIN C , LIU Z F , MA Y Z , et al. Transformer guided self-adaptive network for multi-scale skin lesion image segmentation. Computers in Biology and Medicine, 2024, 169, 107846. doi: 10.1016/j.compbiomed.2023.107846
15	CAO H, WANG Y Y, CHEN J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation[EB/OL]. [2024-08-05]. https://arxiv.org/abs/2105.05537.
16	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2016: 770-778.
17	YUAN Y D , LO Y C . Improving dermoscopic image segmentation with enhanced convolutional-deconvolutional networks. IEEE Journal of Biomedical and Health Informatics, 2019, 23(2): 519- 526. doi: 10.1109/JBHI.2017.2787487
18	LI J , WANG J W , LIN F W , et al. DSEUNet: a lightweight UNet for dynamic space grouping enhancement for skin lesion segmentation. Expert Systems with Applications, 2024, 255, 124544. doi: 10.1016/j.eswa.2024.124544
19	VASWANI A, NOAM S, NIKI P, et al. Attention is all you need[EB/OL]. [2024-08-05]. https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf.
20	ZHENG S X, LU J C, ZHAO H S, et al. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2021: 6877-6886.
21	WANG J C , CHEN F , MA Y X , et al. XBound-former: toward cross-scale boundary modeling in transformers. IEEE Transactions on Medical Imaging, 2023, 42(6): 1735- 1745. doi: 10.1109/TMI.2023.3236037
22	LIN Y, ZHANG D, FANG X, et al. Rethinking boundary detection in deep learning models for medical image segmentation[EB/OL]. [2024-08-05]. https://arxiv.org/abs/2305.00678.
23	GUO Q Q, FANG X Y, WANG L B, et al. LGANet: local-global augmentation network for skin lesion segmentation[C]//Proceedings of the 20th IEEE International Symposium on Biomedical Imaging (ISBI). Washington D.C., USA: IEEE Press, 2023: 1-5.
24	GAO S H , CHENG M M , ZHAO K , et al. Res2Net: a new multi-scale backbone architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652- 662. doi: 10.1109/TPAMI.2019.2938758
25	FU J, LIU J, TIAN H J, et al. Dual attention network for scene segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 3141-3149.
26	GUTMAN D, CODELLA N C F, CELEBI E, et al. Skin lesion analysis toward melanoma detection: a challenge at the international symposium on biomedical imaging (ISBI) 2016, hosted by the international skin imaging collaboration (ISIC)[EB/OL]. [2024-08-05]. https://arxiv.org/abs/1605.01397.
27	CODELLA N, ROTEMBERG V, TSCHANDL P, et al. Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the International Skin Imaging Collaboration (ISIC)[EB/OL]. [2024-08-05]. https://arxiv.org/abs/1902.03368.
28	CHEN J N, LU Y Y, YU Q H, et al. TransUNet: transformers make strong encoders for medical image segmentation[EB/OL]. [2024-08-05]. https://arxiv.org/abs/2102.04306.
29	WU H S , CHEN S H , CHEN G L , et al. FAT-Net: feature adaptive transformers for automated skin lesion segmentation. Medical Image Analysis, 2022, 76, 102327. doi: 10.1016/j.media.2021.102327
30	HUANG Z W , DENG H M , YIN S C , et al. ADF-Net: a novel adaptive dual-stream encoding and focal attention decoding network for skin lesion segmentation. Biomedical Signal Processing and Control, 2024, 91, 105895. doi: 10.1016/j.bspc.2023.105895
31	NAVEED A , NAQVI S S , IQBAL S , et al. RA-Net: region-aware attention network for skin lesion segmentation. Cognitive Computation, 2024, 16(5): 2279- 2296. doi: 10.1007/s12559-024-10304-1
32	LI Y Q , TIAN T H , HU J , et al. SUTrans-NET: a hybrid transformer approach to skin lesion segmentation. PeerJ Computer Science, 2024, 10
33	XU Z J , GUO X Y , WANG J . Enhancing skin lesion segmentation with a fusion of convolutional neural networks and transformer models. Heliyon, 2024, 10(10)
34	XUE Y , CHEN X Y , LIU P , et al. HDS-Net: achieving fine-grained skin lesion segmentation using hybrid encoding and dynamic sparse attention. PLoS One, 2024, 19(3): e0299392. doi: 10.1371/journal.pone.0299392
35	贵向泉, 张馨月, 李立. 高分辨率皮肤黑色素瘤图像的两阶段式分割算法. 计算机工程, 2023, 49(11): 267- 274. doi: 10.19678/j.issn.1000-3428.0066329
	GUI X Q , ZHANG X Y , LI L . Two-stage segmentation algorithm of high resolution skin melanoma image. Computer Engineering, 2023, 49(11): 267- 274. doi: 10.19678/j.issn.1000-3428.0066329
36	JI C , DENG Z H , DING Y , et al. RMMLP: rolling MLP and matrix decomposition for skin lesion segmentation. Biomedical Signal Processing and Control, 2023, 84, 104825. doi: 10.1016/j.bspc.2023.104825
37	JHA D, SMEDSRUD P H, RIEGLER M A, et al. ResUNet++: an advanced architecture for medical image segmentation[C]//Proceedings of the IEEE International Symposium on Multimedia (ISM). Washington D.C., USA: IEEE Press, 2020: 2250-2255.

[1]	LI Haoxuan, ZHANG Zhiyuan, LIU Rui, XU Peihua, TIAN Xin. Climate Downscaling of Image Super-Resolution Based on Implicit Neural Representation [J]. Computer Engineering, 2026, 52(4): 376-385.
[2]	YIN Zhaoliang, HUANG Yuxin, YU Zhengtao, WANG Guanwen, AI Chuanxian. A Method for Analyzing News Themes Involving Cases with Integrated Crime Classification [J]. Computer Engineering, 2025, 51(4): 208-216.
[3]	TANG Jiamin, HAN Hua, HUANG Li. Coarse-grained and Fine-grained Features Extraction Based on Unsupervised Learning in Pedestrian Re-identification [J]. Computer Engineering, 2022, 48(4): 269-275,283.
[4]	FU Jinwu, FAN Zizhu, SHI Linrui, GUO Xinyue, HUANG Yijing. Person Re-Identification Method Based on Multi-Scale and Multi-Granularity Fusion [J]. Computer Engineering, 2022, 48(3): 271-279.
[5]	ZHANG Wenkai,SUN Hao,SUN Xian,WANG Hongqi. Image Set Visual Summarization Based on MFF-GAN [J]. Computer Engineering, 2019, 45(2): 202-206.
[6]	SHI Lipeng,WANG Li. An Enhanced Social Network Representation Algorithm Based on Traversal Constraint and Interactive Information [J]. Computer Engineering, 2018, 44(11): 215-221.
[7]	LI Zhiming. Research on Iris Liveness Detection Algorithm Based on Convolutional Neural Network [J]. Computer Engineering, 2016, 42(5): 239-243,248.
[8]	WANG Li,XU Tiantian. An Improved Canny Algorithm in GVF Snake Model [J]. Computer Engineering, 2016, 42(10): 231-235,241.
[9]	XING Guozheng,JIANG Yuyan,WU Chao,LI Changxun. A Semi-supervised Replicated Softmax Model [J]. Computer Engineering, 2015, 41(9): 209-214.

Please choose a citation manager

Content to export