MA-DenseUNet: A Skin Lesion Segmentation Method Based on Multi-Scale Attention and Bidirectional LSTM
Source abstract
Abstract
Skin diseases are common medical conditions, and early detection significantly contributes to improved cure rates. To address the challenges posed by complex lesion morphology, indistinct boundaries, and image artifacts, this paper proposes a skin lesion segmentation method based on multi-scale attention and bidirectional long short-term memory (Bi-LSTM). Built upon the U-Net architecture, the proposed model enhances the encoder with dense convolutions and an adaptive feature fusion module to strengthen feature extraction and multi-scale information integration. Furthermore, it incorporates both channel and spatial attention mechanisms along with temporal modeling to improve boundary delineation and segmentation accuracy. A generative adversarial network (GAN) is also introduced to refine the segmentation output and boost generalization performance. Experimental results on the ISIC2017 dataset demonstrate that the method achieves an accuracy of 0.950, a Dice coefficient of 0.902, and a mean Intersection over Union (mIoU) of 0.865. These results indicate that the proposed approach effectively improves lesion segmentation performance and offers valuable support for computer-aided diagnosis of skin diseases.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Cutaneous Melanoma Detection and Management · Nonmelanoma Skin Cancer Studies · Skin Protection and Aging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institution of Computer Science and Technology, Changchun Normal University, Changchun 130032, China
Funding
Jilin Provincial Science and Technology Development Plan “Research on Multi-Target Classification Techniques Incorporating Efficient Channel Attention Mechanisms”
References (55)
Show source-provided references
1. Cancer statistics, 202310.3322/caac.21763 ↗
2. Bi-directional dermoscopic feature learning and multi-scale consistent decision fusion for skin lesion segmentation10.1109/TIP.2019.2955297 ↗
3. The global burden of skin disease in 2010: An analysis of the prevalence and impact of skin conditions10.1038/jid.2013.446 ↗
4. Ge, Z., Demyanov, S., Chakravorty, R., and Garnavi, R. (2017). Skin disease recognition using deep saliency features and multimodal learning of dermoscopy and clinical images. Medical Image Computing and Computer Assisted Intervention—MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, 11–13 September 2017, Proceedings, Part III 20, Springer International Publishing.
5. ASCU-Net: Attention gate, spatial and channel attention u-net for skin lesion segmentation10.3390/diagnostics11030501 ↗
6. Lesion border detection in dermoscopy images using ensembles of thresholding methods
7. Sun, G., Ahmed, A., Ebad, S.A., Li, Y., and Bilal, A. (2025). Precision and efficiency in skin cancer segmentation through a dual encoder deep learning model. Sci. Rep., 15.10.1038/s41598-025-88753-3 ↗
8. Alghamdi, N.S., Anbarasi, L.J., Suliman, W., Ravi, V., Jawahar, M., and Sharen, H. (2024). FDUM-Net: An enhanced FPN and U-Net architecture for skin lesion segmentation. Biomed. Signal Process. Control., 91.10.1016/j.bspc.2024.106037 ↗
9. Yuan, C., Zhao, D., and Agaian, S.S. (2024). MUCM-Net: A mamba powered ucm-net for skin lesion segmentation. arXiv.10.37349/emed.2024.00250 ↗
10. Abbas, F., Ahmad, I., Amin, J., Sharif, M.I., and Lali, M.I. (2024). A novel Deeplabv3+ and vision-based transformer model for segmentation and classification of skin lesions. Biomed. Signal Process. Control., 92.10.1016/j.bspc.2024.106084 ↗
11. Cui, X., Lv, H., Chang, Q., Huang, X., Liang, P., and Wu, R. (2024). HSH-UNet: Hybrid selective high order interactive U-shaped model for automated skin lesion segmentation. Comput. Biol. Med., 168.10.1016/j.compbiomed.2023.107798 ↗
12. Suer, S., Kockara, S., and Mete, M. (2011). An improved border detection in dermoscopy images for density based clustering. BMC Bioinform., 12.10.1186/1471-2105-12-S10-S12 ↗
13. AS-Net: Attention Synergy Network for skin lesion segmentation10.1016/j.eswa.2022.117112 ↗
14. Cancer statistics, 2020: Report from national cancer registry programme, India
15. Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., and Tang, X. (2017, January 21–26). Residual attention network for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.683 ↗
16. Glan: Gan assisted lightweight attention network for biomedical imaging based diagnostics10.1007/s12559-023-10131-w ↗
17. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
18. 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: 18th International Conference, Munich, Germany, 5–9 October 2015, Proceedings, Part III 18, Springer International Publishing.
19. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv.
20. Innani, S., Talbar, S., Guntuku, S.C., Bakas, S., Baheti, B., Baid, U., Dutande, P., and Pokuri, V. (2023). Generative adversarial networks based skin lesion segmentation. Sci. Rep., 13.10.1038/s41598-023-39648-8 ↗
21. Zhou, Z., Rahman Siddiquee, M.M., 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: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, 20 September 2018, Proceedings 4, Springer International Publishing.
22. Xiao, X., Lian, S., and Luo, Z. (2018, January 19–21). Weighted res-unet for high-quality retina vessel segmentation. Proceedings of the 2018 9th International Conference on Information Technology in Medicine and Education (ITME), Hangzhou, China.10.1109/ITME.2018.00080 ↗
23. Ruan, J., Xiang, S., and Xie, M. (2022, January 6–8). Malunet: A multi-attention and light-weight unet for skin lesion segmentation. Proceedings of the 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Las Vegas, NV, USA.10.1109/BIBM55620.2022.9995040 ↗
24. Le, P.T., Pham, B.T., and Chang, C.C. (2023). Anti-aliasing attention U-net model for skin lesion segmentation. Diagnostics, 13.10.3390/diagnostics13081460 ↗
25. Ms RED: A novel multi-scale residual encoding and decoding network for skin lesion segmentation10.1016/j.media.2021.102293 ↗
26. CA-Net: Comprehensive attention convolutional neural networks for explainable medical image segmentation10.1109/TMI.2020.3035253 ↗
27. Rahman, C.M.A., Bhuiyan, R.K., and Shyam, S.P. (2024, January 2–4). Attention Enabled MultiResUNet for Bio-Medical Image Segmentation. Proceedings of the 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT), Dhaka, Bangladesh.10.1109/ICEEICT62016.2024.10534532 ↗
28. Wu, R., Liang, P., and Huang, X. (2024). Mhorunet: High-order spatial interaction unet for skin lesion segmentation. Biomed. Signal Process. Control., 88.10.1016/j.bspc.2023.105517 ↗
29. Yu, H., Zhang, W., Li, C., Liu, Z., Qi, W., Guo, Y., and Zhou, S. (2023, January 16–21). MSAU-net: Road extraction based on multi-headed self-attention mechanism and U-net with high resolution remote sensing images. Proceedings of the IGARSS 2023—2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA.10.1109/IGARSS52108.2023.10281628 ↗
30. Shahzaib, I., Zeeshan, M., and Mehmood, M. (2024, January 27–29). TESL-Net: A Transformer-Enhanced CNN for Accurate Skin Lesion Segmentation. Proceedings of the 2024 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Perth, Australia.
31. Rao, A.J., Lakshmanarao, A., DurgaRao, G., and Kumar, G.P. (2024, January 9–10). Innovative Way of Identifying Skin Cancer Model Design with FCNN and LSTM. Proceedings of the 2024 IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT), Uttar Pradesh, India.10.1109/IC2PCT60090.2024.10486410 ↗
32. Optimizing time prediction and error classification in early melanoma detection using a hybrid RCNN-LSTM model10.1002/jemt.24559 ↗
33. Generative Adversarial Nets
34. Step-wise integration of deep class-specific learning for dermoscopic image segmentation10.1016/j.patcog.2018.08.001 ↗
35. Attention-based DenseUnet network with adversarial training for skin lesion segmentation10.1109/ACCESS.2019.2940794 ↗
36. EA-GAN: Enhanced attention generative adversarial network applied to hair removal in dermoscopy images10.1007/s11760-025-03816-2 ↗
37. Bansal, N., and Sridhar, S. (2024). Hexa-gan: Skin lesion image inpainting via hexagonal sampling based generative adversarial network. Biomed. Signal Process. Control., 89.10.1016/j.bspc.2023.105603 ↗
38. Iandola, F., Moskewicz, M., and Karayev, S. (2014). Densenet: Implementing efficient convnet descriptor pyramids. arXiv.
39. Woo, S., Park, J., and Lee, J.Y. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
40. Zhao, L., and Zhang, Z. (2024). A improved pooling method for convolutional neural networks. Sci. Rep., 14.10.1038/s41598-024-51258-6 ↗
41. Binary cross entropy with deep learning technique for image classification10.30534/ijatcse/2020/175942020 ↗
42. Codella, N., Rotemberg, V., and Tschandl, P. (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv.
43. Codella, N.C.F., Gutman, D., and Celebi, M.E. (2018, January 4–7). 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). Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.10.1109/ISBI.2018.8363547 ↗
44. Sharp dense u-net: An enhanced dense u-net architecture for nucleus segmentation10.1007/s13042-023-02017-y ↗
45. Ruan, J., Li, J., and Xiang, S. (2024). Vm-unet: Vision mamba unet for medical image segmentation. arXiv.
46. Hu, X.Z., Jeon, W.S., and Rhee, S.Y. (2023, January 26–29). ATT-UNet: Pixel-wise staircase attention for weed and crop detection. Proceedings of the 2023 International Conference on Fuzzy Theory and Its Applications (iFUZZY), Penghu, Taiwan.10.1109/iFUZZY60076.2023.10324090 ↗
47. Samarakoon, P.N., Tushar, F.I., Dahal, L., Martí, R., and Hasan, K. (2020). DSNet: Automatic dermoscopic skin lesion segmentation. Comput. Biol. Med., 120.10.1016/j.compbiomed.2020.103738 ↗
48. FAT-Net: Feature adaptive transformers for automated skin lesion segmentation10.1016/j.media.2021.102327 ↗
49. Zhang, D., Kang, X., Tian, S., Wu, W., Yu, L., and Zhang, N. (2022). APT-Net: Adaptive encoding and parallel decoding transformer for medical image segmentation. Comput. Biol. Med., 151.10.1016/j.compbiomed.2022.106292 ↗
50. A skin lesion segmentation network with edge and body fusion10.1016/j.asoc.2024.112683 ↗
51. Chen, H., Peng, Z., Huang, X., Li, Z., Deng, Y., Tang, L., and Yin, L. (2024). SCSONet: Spatial-channel synergistic optimization net for skin lesion segmentation. Front. Phys., 12.10.3389/fphy.2024.1388364 ↗
52. Chen, J., Zhang, X., Wang, M., Cao, H., Jiang, D., Wang, Y., and Tian, Q. (2022). Swin-unet: Unet-like pure transformer for medical image segmentation. European Conference on Computer Vision, Springer Nature.
53. Ruan, J., Xie, M., and Gao, J. (2023). Ege-unet: An efficient group enhanced unet for skin lesion segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer Nature.10.1007/978-3-031-43901-8_46 ↗
54. Ziang, H., Zhang, J., and Li, L. (2025). Framework for lung CT image segmentation based on UNet++. arXiv.
55. Automatic skin lesion segmentation using attention residual U-Net with improved encoder-decoder architecture10.1007/s11042-024-18895-5 ↗