基于KFCM与多特征融合的皮肤镜病变区域提取
Extraction of Dermoscopic Lesions Based on KFCM and Multi-Feature Fusion
摘要: 病变轮廓的检测是病灶提取、定性研究和探明病灶与其周围组织间关系的基础。针对皮肤镜图像病变区域灰度强度不均匀导致病变区域难以提取的问题，本文提出一种基于模糊核聚类算法(KFCM)与多特征融合的病变区域提取算法。首先，将原始图像进行模糊核聚类，把得到的聚类结果作为多特征融合轮廓提取模型的初始轮廓，其次利用轮廓曲线演化对图像全局信息与局部信息采用自适应加权，构建符号压力函数(Signed Pressure Force, SPF)，最后利用轮廓曲线演化来分割图像，提取出病变区域。通过真实皮肤镜图像验证了提出的模型在SPF函数和自适应函数引入两方面均能提升提取性能，且在定性和定量对比评价上均优于其他方法，同时对噪声具有鲁棒性。
Abstract: The detection of lesion contour is the basis of lesion extraction, qualitative study and the relation-ship between lesion and surrounding tissue. Aiming at the problem that the lesion area is difficult to extract due to the uneven gray intensity of the lesion area in dermoscopic images, this paper proposes a lesion area extraction algorithm based on fuzzy kernel clustering algorithm (KFCM) and multi-feature fusion. Firstly, the original image is fuzzy kernel clustering, and the clustering result is used as the initial contour of the multi-feature fusion contour extraction model. Secondly, the global and local information of the image is weighted by adaptive contour curve evolution, and a Signed Pressure Force (SPF) function is constructed. Finally, the contour curve evolution was used to segment the image and extract the diseased area. Through real dermoscopic images, it is verified that the proposed model can improve the extraction performance in both SPF function and adaptive function, and is superior to other methods in qualitative and quantitative comparison evaluation, and is robust to noise.
文章引用：栗碧悦, 侯俊, 王子硕, 薛渊, 摆惟圆. 基于KFCM与多特征融合的皮肤镜病变区域提取[J]. 建模与仿真, 2023, 12(5): 4595-4604. https://doi.org/10.12677/MOS.2023.125419

参考文献

[1] Faal, M., Miran Baygi, M.H. and Kabir, E. (2013) Improving the Diagnostic Accuracy of Dysplastic and Melanoma Le-sions Using the Decision Template Combination Method. Skin Research and Technology, 19, e113-e122. [Google Scholar] [CrossRef] [PubMed]
[2] Emre Celebi, M., Wen, Q., Hwang, S., et al. (2013) Lesion Border Detection in Dermoscopy Images Using Ensembles of Thresholding Methods. Skin Research and Technology, 19, e252-e258. [Google Scholar] [CrossRef] [PubMed]
[3] Gaheen, M.A., Ibrahim, E. and Ewees, A.A. (2021) Edge Detection-Based Segmentation for Detecting Skin Lesions. In: Kumar, P., Kumar, Y. and Tawhid, M.A., Eds., Machine Learning, Big Data, and IoT for Medical Informatics, Academic Press, Cambridge, 127-142. [Google Scholar] [CrossRef] 
[4] Liu, Z., Sun, J., Smith, M., et al. (2012) Unsupervised Sub-Segmentation for Pigmented Skin Lesions. Skin Research and Technology, 18, 77-87. [Google Scholar] [CrossRef] [PubMed]
[5] Devanathan, K. (2020) Lesion Segmentation in Dermo-scopic Images Using Superpixel Based Fast Fuzzy C-Means Clustering. 2020 IEEE Congreso Bienal de Argentina (ARGENCON), Resistencia, 1-4 December 2020, 1-6. [Google Scholar] [CrossRef] 
[6] Chan, T.F. and Vese, L.A. (2001) Active Con-tours without Edges. IEEE Transactions on Image Processing, 10, 266-277. [Google Scholar] [CrossRef] [PubMed]
[7] Zhang, K., Zhang, L., Song, H., et al. (2010) Active Contours with Selec-tive Local or Global Segmentation: A New Formulation and Level Set Method. Image and Vision Computing, 28, 668-676. [Google Scholar] [CrossRef] 
[8] Caselles, V., Kimmel, R. and Sapiro, G. (1997) Geodesic Active Contours. International Journal of Computer Vision, 22, 61-79. [Google Scholar] [CrossRef] 
[9] Girolami, M. (2002) Mercer Kernel-Based Clustering in Feature Space. IEEE Transactions on Neural Networks, 13, 780-784. [Google Scholar] [CrossRef] 
[10] Miao, J., Zhou, X. and Huang, T.Z. (2020) Local Segmentation of Images Using an Improved Fuzzy C-Means Clustering Algorithm Based on Self-Adaptive Dictionary Learning. Applied Soft Computing, 91, Article ID: 106200. [Google Scholar] [CrossRef] 
[11] 王星, 宗凯. 基于局部熵的图像分割算法研究与实现[J]. 电子测量技术, 2016, 39(12): 168-171.
[12] 刘莹, 李筠, 杨海马, 等. 结合区域生长与水平集算法的宫颈癌图像分割[J]. 电子测量与仪器学报, 2020, 34(9): 146-152.
[13] 孙林, 柯正友, 冯小博, 等. 基于双符号压力函数的活动轮廓图像分割方法[J]. 计算机工程与应用, 2018, 54(20): 213-218.
[14] Liu, H., Fang, J., Zhang, Z., et al. (2020) A Novel Active Contour Model Guided by Global and Local Signed Energy-Based Pressure Force. IEEE Access, 8, 59412-59426. [Google Scholar] [CrossRef] 
[15] Huang, Q., Zhou, W., Wan, M., et al. (2021) Multi-Feature Driven Active Contour Segmentation Model for Infrared Image with Intensity Inhomogeneity. Optical and Quantum Electronics, 53, Article No. 367. [Google Scholar] [CrossRef] 
[16] Li, C., Kao, C.Y., Gore, J.C., et al. (2008) Minimization of Re-gion-Scalable Fitting Energy for Image Segmentation. IEEE Transactions on Image Processing, 17, 1940-1949. [Google Scholar] [CrossRef] 
[17] Beauchemin, M., Thomson, K.P.B. and Edwards, G. (1998) On the Hausdorff Distance Used for the Evaluation of Segmentation Results. Canadian Journal of Remote Sensing, 24, 3-8. [Google Scholar] [CrossRef] 

为你推荐