Segmentation of Clustered Nuclei With Shape Markers and Marking Function
Segmentation of Clustered Nuclei With Shape Markers and Marking Function
复制标题
DOI：
10.1109/tbme.2008.2008635
复制
发表时间：
2009-03-01
影响因子：
4.6
通讯作者：
Rajapakse, Jagath C.
中科院分区：
文献类型：
--
作者：
Cheng, Jierong;Rajapakse, Jagath C.
我们提出了一种方法，从荧光显微镜细胞图像中分离成簇的细胞核，使用形状标记和标记功能的分水岭算法。形状标记提取使用自适应H-最小变换。引入了基于外距离变换的标记函数来精确地分离聚集的细胞核。与合成图像，我们定量地证明了我们的方法的性能，并提供与现有方法的比较。在小鼠神经元和果蝇细胞图像上，我们比早期方法的分割精度提高了6%-7%。
We present a method to separate clustered nuclei from fluorescence microscopy cellular images, using shape markers and marking function in a watershed-like algorithm. Shape markers are extracted using an adaptive H-minima transform. A marking function based on the outer distance transform is introduced to accurately separate clustered nuclei. With synthetic images, we quantitatively demonstrate the performance of our method and provide comparisons with existing approaches. On mouse neuronal and Drosopbila cellular images, we achieved 6%-7% improvement of segmentation accuracies over earlier methods.