Application of AI Using U-Net in Skin Lesion Segmentation

Serra Aksoy

doi:10.14313/jamris-2026-006

Abstract

Skin lesion segmentation is a critical task in dermatology, essential for the accurate diagnosis and treatment of various skin conditions, including skin cancer. The precise identification of lesion boundaries in medical images significantly helps in early detection and effective management of these conditions. In this study, a U-Net model was employed to perform segmentation of skin lesions, using its advanced encoder-decoder architecture and skip connections to capture fine details and spatial hierarchies within the images. The model yielded an overall accuracy of 95.47%, a precision of 97.21%, a recall of 84.04%, and an F1 score of 90.15%. These results affirm the U-Net model’s proficiency in accurately segmenting skin lesions. The precise boundary delineation provided by the model can help healthcare professionals detect malignant lesions, which often exhibit irregular boundaries, thereby improving diagnostic accuracy. The integration of this model into clinical practice can enhance diagnostic accuracy and efficiency, reduce the workload on healthcare professionals, and improve patient outcomes. The promising performance of the U-Net model emphasizes its potential to revolutionize dermatological diagnostics and support healthcare professionals in delivering timely and precise patient care.

References

J. Li et al., “DSEUNet: A lightweight U-Net for dynamic space grouping enhancement for skin lesion segmentation,” Expert Systems with Applications, vol. 255, Art. no. 124544, Dec. 2024; doi: 10.1016/j.eswa.2024.124544.
Open DOI Search in Google Scholar Back to article
R. J. Hay et al., “The global burden of skin disease in 2010: An analysis of the prevalence and impact of skin conditions,” Journal of Investigative Dermatology, vol. 134, no. 6, pp. 1527–1534, Jun. 2014; doi: 10.1038/jid.2013.446.
Open DOI Search in Google Scholar Back to article
P. Mathur et al., “Cancer statistics, 2020: Report from national cancer registry programme, India,” JCO Global Oncology, no. 6, pp. 1063–1075, Nov. 2020; doi: 10.1200/GO.20.00122.
Open DOI Search in Google Scholar Back to article
J. Wu, E.Z. Chen, R. Rong, X. Li, D. Xu, and H. Jiang, “Skin lesion segmentation with C-UNet,” Proc. 41stAnnu. Int’l Conf. IEEE Eng. Med. Bio. Soc. (EMBC), 2019, pp. 2785–2788; doi: 10.1109/EMBC.2019.8857773.
Open DOI Search in Google Scholar Back to article
P. Tang et al., “Efficient skin lesion segmentation using separable U-Net with stochastic weight averaging,” Computer Methods and Programs in Biomedicine, vol. 178, pp. 289–301, Sep. 2019; doi: 10.1016/j.cmpb.2019.07.005.
Open DOI Search in Google Scholar Back to article
R. Iranpoor, A.S. Mahboob, S. Shahbandegan, and N. Baniasadi, “Skin lesion segmentation using convolutional neural networks with improved U-Net architecture,” Proc. 6th Iranian Conf. Signal Processing and Intelligent Systems (ICSPIS), 2020, pp. 1–5; doi: 10.1109/ICSPIS51611.2020.9349577.
Open DOI Search in Google Scholar Back to article
L. Liu, L. Mou, X.X. Zhu, and M. Mandal, “Skin lesion segmentation based on improved U-Net,” Proc. IEEE Can. Conf. of Electrical and Computer Engineering (CCECE), 2019, pp. 1–4; doi: 10.1109/CCECE.2019.8861848.
Open DOI Search in Google Scholar Back to article
G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, Dec. 2017; doi: 10.1016/j.media.2017.07.005.
Open DOI Search in Google Scholar Back to article
L. Qian, H. Huang, X. Xia, Y. Li, and X. Zhou, “Automatic segmentation method using FCN with multi-scale dilated convolution for medical ultrasound image,” Vis. Comput., vol. 39, no. 11, pp. 5953–5969, Nov. 2023; doi: 10.1007/s00371-022-02705-w.
Open DOI Search in Google Scholar Back to article
G. Zhan, W. Wang, H. Sun, Y. Hou, and L. Feng, “Auto-CSC: A transfer learning based automatic cell segmentation and count framework,” Cyborg Bionic Systems, vol. 2022, 2022, Art. no. 9842349; doi: 10.34133/2022/9842349.
Open DOI Search in Google Scholar Back to article
X. Li, H. Huang, H. Zhao, Y. Wang, and M. Hu, “Learning a convolutional neural network for propagation-based stereo image segmentation,” Vis. Comput., vol. 36, no. 1, pp. 39–52, Jan. 2020; doi: 10.1007/s00371-018-1582-y.
Open DOI Search in Google Scholar Back to article
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation” arXiv, 2015; http://arxiv.org/abs/1505.04597
Search in Google Scholar Back to article
Z. Zhou, M.M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, “U-Net++: A nested U-Net architecture for medical image segmentation,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, D. Stoyanov et al., Eds., Lecture Notes in Computer Science, vol. 11045, Springer, 2018, pp. 3–11; doi: 10.1007/978-3-030-00889-5_1.
Open DOI Search in Google Scholar Back to article
Z. Zhang, Q. Liu, and Y. Wang, “Road extraction by deep residual U-Net,” IEEE Geosci. Remote Sens. Lett., vol. 15, no. 5, pp. 749–753, May 2018; doi: 10.1109/LGRS.2018.2802944.
Open DOI Search in Google Scholar Back to article
D. Jha et al., “ResUNet++: An advanced architecture for medical image segmentation.” arXiv, 2019; http://arxiv.org/abs/1911.07067
Search in Google Scholar Back to article
L.C. Chen, G. Papandreou, F. Schroff, and H. Adam, “Rethinking atrous convolution for semantic Image segmentation.” arXiv, 2017; http://arxiv.org/abs/1706.05587
Search in Google Scholar Back to article
L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation.” arXiv, 2018; http://arxiv.org/abs/1802.02611
Search in Google Scholar Back to article
T.Y Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection.” arXiv, 2017; http://arxiv.org/abs/1612.03144
Search in Google Scholar Back to article
T. Fan, G. Wang, Y. Li, and H. Wang, “MA-Net: A multi-scale attention network for liver and tumor segmentation,” IEEE Access, vol. 8, pp. 179656–179665, 2020; doi: 10.1109/ACCESS.2020.3025372.
Open DOI Search in Google Scholar Back to article
A. Chaurasia and E. Culurciello, “LinkNet: Exploiting encoder representations for efficient semantic segmentation,” Proc. IEEE Visual Communications and Image Processing (VCIP), 2017, pp. 1–4; doi: 10.1109/VCIP.2017.8305148.
Open DOI Search in Google Scholar Back to article
H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network.” arXiv, 2017; http://arxiv.org/abs/1612.01105
Search in Google Scholar Back to article
S.M. Jaisakthi, P. Mirunalini, and C. Aravindan, “Automated skin lesion segmentation of dermoscopic images using GrabCut and k-means algorithms,” IET Computer Vision, vol. 12, no. 8, pp. 1088–1095, Dec. 2018; doi: 10.1049/iet-cvi.2018.5289.
Open DOI Search in Google Scholar Back to article
M. Aljanabi, Y.E. Ozok, J. Rahebi, and A.S. Abdullah, “Skin lesion segmentation method for dermoscopy images using artificial bee colony algorithm,” Symmetry, vol. 10, no. 8, p. 347, Aug. 2018; doi: 10.3390/sym10080347.
Open DOI Search in Google Scholar Back to article
M. Berseth, “ISIC 2017 - Skin lesion analysis towards melanoma detection.” arXiv, 2017; doi: 10.48550/ARXIV.1703.00523.
Open DOI Search in Google Scholar Back to article
R. Mishra and O. Daescu, “Deep learning for skin lesion segmentation,” Proc. IEEEIn’l Conf. Bioinformatics Biomedicine (BIBM), 2017, pp. 1189–1194; doi: 10.1109/BIBM.2017.8217826.
Open DOI Search in Google Scholar Back to article

Application of AI Using U-Net in Skin Lesion Segmentation

Abstract

Paradigm

My account