基于局部二值模式聚类的皮肤图像精确分割

题目：

Accurate Segmentation of Dermoscopic Images based on Local Binary Pattern Clustering

作者：

Pedro MM Pereira，Rui Fonseca-Pinto，Rui Pedro Paiva，Luis MN Tavora，Pedro AA Assuncao，Sergio MM de Faria1

来源：

Computer Vision and Pattern Recognition (cs.CV)

(Submitted on 17 Feb 2019)

链接：

摘要

分割是皮肤镜图像处理中的关键阶段，其中定义皮肤损伤的边界线的准确性对于随后的算法（例如，分类）和计算机辅助的严重医学病症的早期诊断是最重要的。本文提出了一种基于局部二值模式（LBP）的新型分割方法，其中LBP和K-Means聚类相结合，实现了皮肤镜图像的详细描绘。与通常的皮肤病学家类似的分割（即，可用的地面实况）相比，所提出的方法能够找到更真实的皮肤损伤边界，即更详细的细节。结果还显示出不同性能测量之间的可变性降低，并且它们在不同图像中是一致的。所提出的方法可以应用于适合于病变边界生长特异性的基于细胞的类似分割。因此，该方法适合于跟踪与皮肤黑素细胞图像中的病变边界几何形状相关的生长动力学。

英文原文

Segmentation is a key stage in dermoscopic image processing, where the accuracy of the border line that defines skin lesions is of utmost importance for subsequent algorithms (e.g., classification) and computer-aided early diagnosis of serious medical conditions. This paper proposes a novel segmentation method based on Local Binary Patterns (LBP), where LBP and K-Means clustering are combined to achieve a detailed delineation in dermoscopic images. In comparison with usual dermatologist-like segmentation (i.e., the available ground-truth), the proposed method is capable of finding more realistic borders of skin lesions, i.e., with much more detail. The results also exhibit reduced variability amongst different performance measures and they are consistent across different images. The proposed method can be applied for cell-based like segmentation adapted to the lesion border growing specificities. Hence, the method is suitable to follow the growth dynamics associated with the lesion border geometry in skin melanocytic images.