Improved Segmentation of Skin Lesions Using Attention-Enhanced Residual U-Net

International Journal of Computer Science and Engineering

© 2024 by SSRG - IJCSE Journal

Volume 11 Issue 12

Year of Publication : 2024

Authors : Saleh Alghamdi

10.14445/23488387/IJCSE-V11I12P104

How to Cite?

Saleh Alghamdi, "Improved Segmentation of Skin Lesions Using Attention-Enhanced Residual U-Net," SSRG International Journal of Computer Science and Engineering , vol. 11,  no. 12, pp. 23-30, 2024. Crossref, https://doi.org/10.14445/23488387/IJCSE-V11I12P104

Abstract:

Accurate segmentation of skin lesions is critical for early skin cancer identification and treatment. Conventional U-Net architectures have been widely utilized in medical image segmentation for their ability to capture intricate details effectively. However, these models often encounter challenges in grasping contextual information and managing complex lesion boundaries. We propose an enhanced segmentation model, the attention-based residual U-Net, which incorporates attention mechanisms and residual connections into the traditional U-Net architecture. The attention mechanism enables the network to concentrate on relevant regions of the input image, improving feature extraction, while residual connections aid in training deeper networks by tackling the issue of vanishing gradients. Assessed on a publicly available dermoscopic image dataset (PH2 dataset), our model demonstrates significant improvements in segmentation accuracy (96.55%) and boundary outlining, attaining higher dice coefficients (89.54%) and reduced segmentation errors. The proposed model displays resilience across various lesion variations and imaging conditions, making it a promising tool for clinical applications in dermatology.

Keywords:

Skin lesion segmentation, Attention mechanism, Residual U-Net, Deep learning, Medical image analysis.

References:

[1] Cancer, World Health Organization, 2019. [Online]. Available: https://www.who.int/health-topics/cancer
[2] Skin Cancer, American Cancer Society, 2025. [Online]. Available: https://www.cancer.org/cancer/types/skin-cancer.html
[3] N. C. F. Codella et al., “Deep Learning Ensembles for Melanoma Recognition in Dermoscopy Images,” IBM Journal of Research and Development, vol. 61, no. 4/5, pp. 5:1-5:15, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Olaf Ronneberger, Philipp Fischer, and Thomas Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015: 18th International Conference, Munich, Germany, pp. 234-241, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Ozgun Cicek et al., “3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation,” Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016: 19th International Conference, Athens, Greece, pp. 424-432, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Qiang Zuo, Songyu Chen, and Zhifang Wang, “R2AU-Net: Attention Recurrent Residual Convolutional Neural Network for Multimodal Medical Image Segmentation,” Security and Communication Networks, vol. 2021, no. 1, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Ozan Oktay et al., “Attention U-Net: Learning Where to Look for the Pancreas,” 1st Conference on Medical Imaging with Deep Learning (MIDL 2018), Amsterdam, The Netherlands, pp. 1-10, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Foivos I. Diakogiannis et al., “ResUNet-a: A Deep Learning Framework for Semantic Segmentation of Remotely Sensed Data,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 162, pp. 94-114, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Teresa Mendonca et al., “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, Japan, pp. 5437-5440, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Omran Salih et al., “An Overview of Skin Lesion Segmentation Methods: Techniques, Challenges, and Future Directions,” 2023 IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), Benghazi, Libya, pp. 744-749, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Duan Wang, “Skin Lesion Segmentation of Dermoscopy Images Using U-Net,” Applied and Computational Engineering, vol. 6, pp. 840-847, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Hanene Sahli, Amine Ben Slama, and Mounir Sayadi, “Skin Lesion Segmentation Based on Modified U-NET Architecture,” 2023 IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET), Hammamet, Tunisia, pp. 1-5, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Nidhal Khdhair El Abbadi, and Abbas Hussien Miry, “Automatic Segmentation of Skin Lesions Using Histogram Thresholding,” Journal of Computer Science, vol. 10, no. 4, pp. 632-639, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Farhan Riaz et al., “Active Contours Based Segmentation and Lesion Periphery Analysis for Characterization of Skin Lesions in Dermoscopy Images,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 2, pp. 489-500 , 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Lina Liu et al., “Automatic Skin Lesion Classification Based on Mid-Level Feature Learning,” Computerized Medical Imaging and Graphics, vol. 84, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Jonathan Long, Evan Shelhamer, and Trevor Darrell, “Fully Convolutional Networks for Semantic Segmentation,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431-3440, 2015.
[Google Scholar] [Publisher Link]
[17] Pengfei Zhou, Xuefeng Liu, and Jichuan Xiong, “Skin Lesion Image Segmentation Based on Lightweight Multi-Scale U-Shaped Network,” Biomedical Physics and Engineering Express, vol. 9, no. 5, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Omran Salih et al., “FFT-Assisted U-Net Architecture for Improved Skin Lesion Segmentation,” 2023 IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), Benghazi, Libya, pp. 480-485, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[20] S. Manivannan, and N. Venkateswaran, “Skin Lesion Segmentation using Residual U-NET,” 2023 10th International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India, pp. 405-409, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Dasari Anantha Reddy et al., “Enhanced U-Net Segmentation with Ensemble Convolutional Neural Network for Automated Skin Disease Classification,” Knowledge and Information Systems, vol. 65, no. 10, pp. 4111-4156, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Shubham Innani et al., “Generative Adversarial Networks Based Skin Lesion Segmentation,” Scientific Reports, vol. 13, no. 1, pp. 1-10, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Sanghyun Woo et al., “CBAM: Convolutional Block Attention Module,” Computer Vision – ECCV 2018, 15th European Conference, Munich, Germany, pp. 3-19, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Aasia Rehman, Muheet A. Butt, and Majid Zaman, “Attention Res-UNet: Attention Residual UNet With Focal Tversky Loss for Skin Lesion Segmentation,” International Journal of Decision Support System Technology, vol. 15, no. 1, pp. 1-17, 2023.[Google Scholar] [Publisher Link]