Volume 2 · Issue 6 (2025)
HVSS-Net: A Parallel Heterogeneous Feature Extraction Network for Dermoscopic Image Segmentation
Sitong Wu
Shenyang University of Technology, Shenyang 110870, China
Abstract: Accurate segmentation of lesion regions in dermoscopic images plays a critical role in computer-aided diagnosis of skin cancer. However, existing segmentation methods often struggle with insufficient global semantic modeling and limited fine-grained texture representation, which leads to blurred lesion boundaries and unstable segmentation performance. To address these challenges, this paper proposes HVSS-Net, a novel dermoscopic image segmentation network built upon an improved Mamba-UNet framework. In HVSS-Net, a dedicated HVSS feature extraction unit is designed to perform parallel heterogeneous feature extraction. This unit consists of three complementary sub-modules that focus on global contextual information, local texture characterization, and boundary-aware feature learning, respectively. The multi-path features are further integrated through a global fusion module to enhance representation robustness. Extensive experiments are conducted on three public dermoscopic datasets, namely ISIC2016, ISIC2018, and PH2. The proposed HVSS-Net achieves Dice scores of 89.95%, 87.95%, and 93.52%, respectively, demonstrating consistent performance across different datasets. Comparative results show that HVSS-Net outperforms multiple state-of-the-art methods in terms of segmentation accuracy and boundary detail preservation. These results indicate that HVSS-Net provides a stable and effective solution for accurate lesion segmentation in dermoscopic images and has strong potential for clinical auxiliary diagnosis applications.
Keywords: Dermoscopic image segmentation; Parallel heterogeneous feature extraction; Wavelet-based convolution; Boundary enhancement; Deep learning
References
[1]
Celebi M E, Iyatomi H, Schaefer G, et al. Lesion border detection in dermoscopy images. Computerized medical imaging and graphics, 2009,33(2):148-153.
[2]
Litjens G, Kooi T, Bejnordi B E, et al. A survey on deep learning in medical image analysis. Medical image analysis, 2017,42:60-88.
[3]
Abbas Q, Celebi M E, García I F. Hair removal methods: A comparative study for dermoscopy images. Biomedical Signal Processing and Control, 2011,6(4):395-404.
[4]
Kass M, Witkin A, Terzopoulos D. Snakes: Active contour models. International journal of computer vision, 1988,1(4):321-331.
[5]
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation: International Conference on Medical image computing and computer-assisted intervention, 2015. Springer.
[6]
Oktay O, Schlemper J, Folgoc L L, et al. Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999, 2018.
[7]
Dosovitskiy A. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
[8]
Liu Z, Lin Y, Cao Y, et al. Swin transformer: Hierarchical vision transformer using shifted windows: Proceedings of the IEEE/CVF international conference on computer vision, 2021.
[9]
Chen J, Lu Y, Yu Q, et al. Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306, 2021.
[10]
Cao H, Wang Y, Chen J, et al. Swin-unet: Unet-like pure transformer for medical image segmentation: European conference on computer vision, 2022. Springer.
[11]
Wang H, Cao P, Wang J, et al. Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer: Proceedings of the AAAI conference on artificial intelligence, 2022.
[12]
Hatamizadeh A, Tang Y, Nath V, et al. Unetr: Transformers for 3d medical image segmentation: Proceedings of the IEEE/CVF winter conference on applications of computer vision, 2022.
[13]
Gu A, Dao T. Mamba: Linear-time sequence modeling with selective state spaces: First conference on language modeling, 2024.
[14]
Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015.
[15]
Zhou Z, Rahman Siddiquee M M, Tajbakhsh N, et al. Unet++: A nested u-net architecture for medical image segmentation: International workshop on deep learning in medical image analysis, 2018. Springer.
[16]
Huang X, Deng Z, Li D, et al. Missformer: An effective medical image segmentation transformer. arXiv preprint arXiv:2109.07162, 2021.
[17]
Chen R, He S, Xie J, et al. MedFuseNet: fusing local and global deep feature representations with hybrid attention mechanisms for medical image segmentation. Scientific Reports, 2025,15(1):5093.
[18]
Huo X, Sun G, Tian S, et al. HiFuse: Hierarchical multi-scale feature fusion network for medical image classification. Biomedical Signal Processing and Control, 2024,87:105534.
[19]
Finder S E, Amoyal R, Treister E, et al. Wavelet convolutions for large receptive fields: European Conference on Computer Vision, 2024. Springer.
[20]
Huang G, Liu Z, Van Der Maaten L, et al. Densely connected convolutional networks: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017.
[21]
Qi Y, He Y, Qi X, et al. Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation: Proceedings of the IEEE/CVF international conference on computer vision, 2023.
Download PDF