WMSM-Net: Wavelet-enhanced Mamba with spatial-channel mutual-feedback attention network for skin lesion segmentation

Xinrong Fu; Jianhua Song; Xinying Huang; Yu Chen; Hao Liu; Xinrong Fu; Jianhua Song; Xinying Huang; Yu Chen; Hao Liu

doi:10.3934/era.2026301

Electronic Research Archive

2026, Volume 34, Issue 9: 6933-6956. doi: 10.3934/era.2026301

Previous Article Next Article

Research article Special Issues

WMSM-Net: Wavelet-enhanced Mamba with spatial-channel mutual-feedback attention network for skin lesion segmentation

1.
College of Physics and Information Engineering, Minnan Normal University, Zhangzhou 363000, China
2.
Key Laboratory of Light Field Manipulation and System Integration Applications in Fujian Province, Minnan Normal University, Zhangzhou 363000, China

Received: 22 May 2026 Revised: 07 July 2026 Accepted: 24 July 2026 Published: 12 August 2026

Accurate skin lesion segmentation remains challenging due to vague boundaries and heavy artifact interference in complex backgrounds. To address these issues, we introduce WMSM-Net, a frequency-space collaborative network built upon the visual state space (Mamba) architecture. WMSM-Net proposes a Wavelet-enhanced Visual State Space Block (W-VSSB) to extract high-frequency boundary details and mitigate edge loss. Concurrently, a Bidirectional Mutual-Feedback Spatial-Channel Attention Bridge (MF-SCAB) was constructed to deliver two-way guidance across spatial and channel dimensions, enhancing the perception of subtle lesions. Feature transitions were further optimized via dynamic gated fusion to suppress background noise. Extensive experiments demonstrated that WMSM-Net achieves state-of-the-art performance, yielding Dice coefficients of 91.01%, 91.08%, and 94.06% for the ISIC 2017, ISIC 2018, and PH2 datasets, respectively. The code is publicly available at https://github.com/fuxinrong2024/WMSM-Net.
- skin lesion segmentation,
- Mamba model,
- wavelet enhancement,
- attention mechanism,
- frequency-domain and spatial-domain collaboration
Citation: Xinrong Fu, Jianhua Song, Xinying Huang, Yu Chen, Hao Liu. WMSM-Net: Wavelet-enhanced Mamba with spatial-channel mutual-feedback attention network for skin lesion segmentation[J]. Electronic Research Archive, 2026, 34(9): 6933-6956. doi: 10.3934/era.2026301

Related Papers:

Abstract

Accurate skin lesion segmentation remains challenging due to vague boundaries and heavy artifact interference in complex backgrounds. To address these issues, we introduce WMSM-Net, a frequency-space collaborative network built upon the visual state space (Mamba) architecture. WMSM-Net proposes a Wavelet-enhanced Visual State Space Block (W-VSSB) to extract high-frequency boundary details and mitigate edge loss. Concurrently, a Bidirectional Mutual-Feedback Spatial-Channel Attention Bridge (MF-SCAB) was constructed to deliver two-way guidance across spatial and channel dimensions, enhancing the perception of subtle lesions. Feature transitions were further optimized via dynamic gated fusion to suppress background noise. Extensive experiments demonstrated that WMSM-Net achieves state-of-the-art performance, yielding Dice coefficients of 91.01%, 91.08%, and 94.06% for the ISIC 2017, ISIC 2018, and PH2 datasets, respectively. The code is publicly available at https://github.com/fuxinrong2024/WMSM-Net.

References

[1]	C. Dayananda, N. Yamanakkanavar, T. Nguyen, B. Lee, AMCC-Net: An asymmetric multi-cross convolution for skin lesion segmentation on dermoscopic images, Eng. Appl. Artif. Intell., 122 (2023), 106154. https://doi.org/10.1016/j.engappai.2023.106154 doi: 10.1016/j.engappai.2023.106154
[2]	S. Qiu, C. Li, Y. Feng, S. Zuo, H. Liang, A. Xu, GFANet: Gated fusion attention network for skin lesion segmentation, Comput. Biol. Med., 155 (2023), 106462. https://doi.org/10.1016/j.compbiomed.2022.106462 doi: 10.1016/j.compbiomed.2022.106462
[3]	C. Dong, D. Dai, Y. Zhang, C. Zhang, Z. Li, S. Xu, Learning from dermoscopic images in association with clinical metadata for skin lesion segmentation and classification, Comput. Biol. Med., 152 (2023), 106321. https://doi.org/10.1016/j.compbiomed.2022.106321 doi: 10.1016/j.compbiomed.2022.106321
[4]	H. Wu, S. Chen, G. Chen, W. Wang, B. Lei, Z. Wen, FAT-Net: Feature adaptive transformers for automated skin lesion segmentation, Med. Image Anal., 76 (2022), 102327. https://doi.org/10.1016/j.media.2021.102327 doi: 10.1016/j.media.2021.102327
[5]	M. Karri, C. S. R. Annavarapu, U. R. Acharya, Skin lesion segmentation using two-phase cross-domain transfer learning framework, Comput. Methods Programs Biomed., 231 (2023), 107408. https://doi.org/10.1016/j.cmpb.2023.107408 doi: 10.1016/j.cmpb.2023.107408
[6]	O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer International Publishing, Cham, (2015), 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
[7]	Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, J. Liang, Unet++: A nested u-net architecture for medical image segmentation, in International Workshop on Deep Learning in Medical Image Analysis, Springer International Publishing, Cham, (2018), 3–11. https://doi.org/10.1007/978-3-030-00889-5_1
[8]	F. Isensee, P. F. Jaeger, S. A. A. Kohl, J. Petersen, K. H. Maier-Hein, nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation, Nat. Methods, 18 (2021), 203–211. https://doi.org/10.1038/s41592-020-01008-z
[9]	Y. Peng, D. Z. Chen, M. Sonka, U-Net v2: Rethinking the skip connections of U-Net for medical image segmentation, in 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), IEEE, (2025), 1–5. https://doi.org/10.1109/ISBI60581.2025.10980742
[10]	J. Ruan, S. Xiang, M. Xie, T. Liu, Y. Fu, Malunet: A multi-attention and light-weight unet for skin lesion segmentation, in 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, (2022), 1150–1156. https://doi.org/10.1109/BIBM55620.2022.9995040
[11]	L. Yuan, J. Song, Y. Fan, FM-Unet: Biomedical image segmentation based on feedback mechanism Unet, Math. Biosci. Eng., 20 (2023), 12039–12055. https://doi.org/10.3934/mbe.2023535 doi: 10.3934/mbe.2023535
[12]	L. Yuan, J. Song, Y. Fan, MCNMF-Unet: A mixture Conv-MLP network with multi-scale features fusion Unet for medical image segmentation, PeerJ Comput. Sci., 10 (2024), 1798. https://doi.org/10.7717/peerj-cs.1798 doi: 10.7717/peerj-cs.1798
[13]	J. Chen, J. Mei, X. Li, Y. Lu, Q. Yu, Q. Wei, et al., TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers, Med. Image Anal., 97 (2024), 103280. https://doi.org/10.1016/j.media.2024.103280 doi: 10.1016/j.media.2024.103280
[14]	H. Cao, Y. Wang, J. Chen, D. Jiang, X. Zhang, Q. Tian, et al., Swin-unet: Unet-like pure transformer for medical image segmentation, in European Conference on Computer Vision, Springer Nature Switzerland, Cham, (2022), 205–218. https://doi.org/10.1007/978-3-031-25066-8_9
[15]	Y. Zhang, H. Liu, Q. Hu, Transfuse: Fusing transformers and cnns for medical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer International Publishing, Cham, (2021), 14–24. https://doi.org/10.1007/978-3-030-87193-2_2
[16]	Y. Fan, J. Song, L. Yuan, Y. Jia, HCT-Unet: Multi-target medical image segmentation via a hybrid CNN-transformer Unet incorporating multi-axis gated multi-layer perceptron, Visual Comput., 41 (2025), 3457–3472. https://doi.org/10.1007/s00371-024-03612-y doi: 10.1007/s00371-024-03612-y
[17]	Y. Fan, J. Song, Y. Lu, X. Fu, X. Huang, L. Yuan, DPUSegDiff: A dual-path U-Net segmentation diffusion model for medical image segmentation, Electron. Res. Arch., 33 (2025), 2947–2971. https://doi.org/10.3934/era.2025129 doi: 10.3934/era.2025129
[18]	A. L. Sharma, K. Sharma, P. Ghosal, Skin lesion segmentation: A systematic review of computational techniques, tools, and future directions, Comput. Biol. Med., 196 (2025), 110842. https://doi.org/10.1016/j.compbiomed.2025.110842 doi: 10.1016/j.compbiomed.2025.110842
[19]	A. Gu, T. Dao, Mamba: Linear-time sequence modeling with selective state spaces, preprint, arXiv: 2312.00752.
[20]	Y. Liu, Y. Tian, Y. Zhao, H. Yu, L. Xie, Y. Wang, et al., Vmamba: Visual state space model, Adv. Neural Inf. Process. Syst., 37 (2024), 103031–103063. https://doi.org/10.52202/079017-3273 doi: 10.52202/079017-3273
[21]	Z. Wang, J. Q. Zheng, Y. Zhang, G. Cui, L. Li, Mamba-unet: Unet-like pure visual mamba for medical image segmentation, preprint, arXiv: 2402.05079.
[22]	J. Ma, F. Li, B. Wang, U-mamba: Enhancing long-range dependency for biomedical image segmentation, preprint, arXiv: 2401.04722.
[23]	H. Chen, Q. Liu, Z. Fu, L. Liu, UM-Mamba: An efficient U-network with medical visual state space for medical image segmentation, Comput. Vision Image Understanding, 259 (2025), 104436. https://doi.org/10.1016/j.cviu.2025.104436 doi: 10.1016/j.cviu.2025.104436
[24]	C. Yu, Z. Fu, Z. Zhang, C. Chen, MMU-Net: An efficient medical image segmentation model combining multi-scale feature information, Biomed. Signal Process. Control, 112 (2026), 108265. https://doi.org/10.1016/j.bspc.2025.108265 doi: 10.1016/j.bspc.2025.108265
[25]	J. Ruan, J. Li, S. Xiang, Vm-unet: Vision mamba unet for medical image segmentation, ACM Trans. Multimedia Comput. Commun. Appl., 2024 (2024). https://doi.org/10.1145/3767748
[26]	R. Arora, B. Raman, K. Nayyar, R. Awasthi, Automated skin lesion segmentation using attention-based deep convolutional neural network, Biomed. Signal Process. Control, 65 (2021), 102358. https://doi.org/10.1016/j.bspc.2020.102358 doi: 10.1016/j.bspc.2020.102358
[27]	K. Hu, J. Lu, D. Lee, D. Xiong, Z. Chen, AS-Net: Attention synergy network for skin lesion segmentation, Expert Syst. Appl., 201 (2022), 117112. https://doi.org/10.1016/j.eswa.2022.117112 doi: 10.1016/j.eswa.2022.117112
[28]	Y. Sun, Y. Dai, Q. Zhang, Y. Wang, S. Xu, C. Lian, MSCA-Net: Multi-scale contextual attention network for skin lesion segmentation, Pattern Recogn., 139 (2023), 109524. https://doi.org/10.1016/j.patcog.2023.109524 doi: 10.1016/j.patcog.2023.109524
[29]	M. Bao, S. Lyu, Z. Xu, Q. Zhao, C. Zeng, W. Bai, et al., ASP-VMUNet: Atrous shifted parallel vision mamba U-Net for skin lesion segmentation, preprint, arXiv: 2503.19427.
[30]	S. Zou, M. Zhang, B. Fan, Z. Zhou, X. Zou, Skinmamba: A precision skin lesion segmentation architecture with cross-scale global state modeling and frequency boundary guidance, preprint, arXiv: 2409.10890.
[31]	T. N. Q. Nguyen, Q. H. Ho, D. T. Nguyen, H. M. Q. Le, V. T. Pham, T. T. Tran, MambaU-lite: A lightweight model based on Mamba and integrated channel-spatial attention for skin lesion segmentation, in The International Conference on Intelligent Systems & Networks, Springer Nature Singapore, Singapore, (2025), 49–58. https://doi.org/10.1007/978-981-95-1746-6_6
[32]	H. Liu, Y. Fu, S. Zhang, J. Liu, Y. Wang, G. Wang, et al., GCHA-Net: Global context and hybrid attention network for automatic liver segmentation, Comput. Biol. Med., 152 (2023), 106352. https://doi.org/10.1016/j.compbiomed.2022.106352 doi: 10.1016/j.compbiomed.2022.106352
[33]	H. Liu, W. Sun, Y. Fu, S. Zhang, J. Jin, J. Fang, et al., Lifting wavelet transform-guided network with histogram attention for liver segmentation in CT scans, Inf. Fusion, 170 (2026), 104153. https://doi.org/10.1016/j.inffus.2026.104153 doi: 10.1016/j.inffus.2026.104153
[34]	J. Fang, S. Qi, Y. Fu, S. Zhang, J. Jin, D. Wang, et al., Semi-supervised dual-teacher comparative learning with bidirectional balanced copy-paste for medical image segmentation, Biomed. Signal Process. Control, 119 (2026), 109985. https://doi.org/10.1016/j.bspc.2026.109985 doi: 10.1016/j.bspc.2026.109985
[35]	H. Liu, J. Yang, Y. Fu, S. Zhang, D. Wang, J. Fang, et al., Adaptive modality-channel-search Hadamard multimodal fusion network for multi-phase liver tumor segmentation, Biomed. Signal Process., 124 (2026), 110695. https://doi.org/10.1016/j.bspc.2026.110695 doi: 10.1016/j.bspc.2026.110695
[36]	N. C. F. Codella, D. Gutman, M. E. Celebi, B. Helba, M. A. Marchetti, S. W. Dusza, et al., 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), in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), IEEE, (2018), 168–172. https://doi.org/10.1109/ISBI.2018.8363547
[37]	N. Codella, V. Rotemberg, P. Tschandl, M. E. Celebi, S. Dusza, D. Gutman, et al., Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (ISIC), preprint, arXiv: 1902.03368.
[38]	T. Mendonça, P. M. Ferreira, J. S. Marques, A. R. S. Marcal, J. Rozeira, PH²-A dermoscopic image database for research and benchmarking, in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, (2013), 5437–5440. https://doi.org/10.1109/EMBC.2013.6610779

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)