Serin Faruk, Erturkler Metin, Gul Mehmet
Department of Computer Engineering, Faculty of Engineering, Munzur University, Tunceli, Turkey.
Department of Computer Engineering, Faculty of Engineering, Inonu University, Malatya, Turkey.
Comput Methods Programs Biomed. 2017 Nov;151:57-70. doi: 10.1016/j.cmpb.2017.08.010. Epub 2017 Aug 24.
Nuclei segmentation is a common process for quantitative analysis of histopathological images. However, this process generally results in overlapping of nuclei due to the nature of images, the sample preparation and staining, and image acquisition processes as well as insufficiency of 2D histopathological images to represent 3D characteristics of tissues. We present a novel algorithm to split overlapped nuclei.
The histopathological images are initially segmented by K-Means segmentation algorithm. Then, nuclei cluster are converted to binary image. The overlapping is detected by applying threshold area value to nuclei in the binary image. The splitting algorithm is applied to the overlapped nuclei. In first stage of splitting, circles are drawn on overlapped nuclei. The radius of the circles is calculated by using circle area formula, and each pixel's coordinates of overlapped nuclei are selected as center coordinates for each circle. The pixels in the circle that contains maximum number of intersected pixels in both the circle and the overlapped nuclei are removed from the overlapped nuclei, and the filled circle labeled as a nucleus.
The algorithm has been tested on histopathological images of healthy and damaged kidney tissues and compared with the results provided by an expert and three related studies. The results demonstrated that the proposed splitting algorithm can segment the overlapping nuclei with accuracy of 84%.
The study presents a novel algorithm splitting the overlapped nuclei in histopathological images and provides more accurate cell counting in histopathological analysis. Furthermore, the proposed splitting algorithm has the potential to be used in different fields to split any overlapped circular patterns.
细胞核分割是组织病理学图像定量分析的常见过程。然而，由于图像的性质、样本制备与染色、图像采集过程以及二维组织病理学图像在表示组织三维特征方面的不足，该过程通常会导致细胞核重叠。我们提出了一种新的算法来分割重叠的细胞核。
首先使用K-Means分割算法对组织病理学图像进行分割。然后，将细胞核聚类转换为二值图像。通过对二值图像中的细胞核应用阈值面积值来检测重叠情况。将分割算法应用于重叠的细胞核。在分割的第一阶段，在重叠的细胞核上绘制圆圈。利用圆面积公式计算圆圈的半径，并将重叠细胞核的每个像素坐标作为每个圆圈的中心坐标。从重叠细胞核中移除圆圈内且在圆圈和重叠细胞核中相交像素数量最多的像素，并将填充的圆圈标记为一个细胞核。
该算法已在健康和受损肾脏组织的组织病理学图像上进行了测试，并与一位专家和三项相关研究的结果进行了比较。结果表明，所提出的分割算法能够以84%的准确率分割重叠的细胞核。
本研究提出了一种在组织病理学图像中分割重叠细胞核的新算法，并在组织病理学分析中提供了更准确的细胞计数。此外，所提出的分割算法有潜力应用于不同领域，以分割任何重叠的圆形图案。
