Intensity inhomogeneity is one of the main challenges in automatic medical image segmentation. In this paper, fuzzy local intensity clustering (FLIC), which is based on the combination of level set algorithm and fuzzy clustering, is proposed to mitigate the effect of intensity variation and noise contamination. For the FLIC method, the segmentation and bias modification are carried out in a fully automatic and simultaneous manner through the local clustering of intensity and selection of the initial contour by the fuzzy method. Besides, the local entropy is integrated into the FLIC function to improve the contour evolution. Experimental results on inhomogeneous medical images indicate the superiority of the FLIC model over the other state-of-the-art segmentation methods in terms of accuracy, robustness, and computational time.

中文翻译：

---

用于自动医学图像分割的模糊局部强度聚类（FLIC）模型

强度不均匀是自动医学图像分割的主要挑战之一。在本文中，提出了基于水平集算法和模糊聚类相结合的模糊局部强度聚类（FLIC）来减轻强度变化和噪声污染的影响。对于FLIC方法，通过局部强度聚类和模糊方法选择初始轮廓，以全自动和同步的方式进行分割和偏差修改。此外，局部熵被集成到 FLIC 函数中以改善轮廓演化。非均匀医学图像的实验结果表明 FLIC 模型在准确性、鲁棒性和计算时间方面优于其他最先进的分割方法。