宫颈细胞核质自动分离算法研究

Study on Automatic Separation Algorithm of Cervical Cytoplasm

宫颈细胞核质分离在宫颈细胞形态学研究中是十分重要且具有挑战性的环节。论文提出了一种基于Grab Cut算法结合Canny算子边缘检测高效分离宫颈细胞核与细胞质的方法。对获取宫颈细胞图像进行灰度变化预处理求得灰度直方图,根据直方图求解确定Canny算子双阈值,进而获取宫颈细胞核和细胞质的轮廓;根据获取的轮廓利用改进的Grab Cut算法进行核质分离,并且针对Grab Cut算法进行相应改进,使其高斯混合模型的参数的确定效率提升。实验结果表明,该算法不仅有较好的分割效果而且分割准确率与效率也很高。

Nuclear-cytoplasmic separation of cervical cells is a very important and challenging step in the study of cervical cell morphology.A new method for the separation of cervical nucleus and cytoplasm is proposed,which is based on the Grab Cut al⁃gorithm and Canny operator edge detection.The gray-level histogram is obtained by gray-level change pretreatment of cervical cell image,and the Canny operator double threshold is determined by histogram solution,then the contour of cervical cell nucleus and cytoplasm is obtained.According to the contour obtained,the improved Grab Cut algorithm is used to separate nucleus and cyto⁃plasm,and the corresponding improvement is made for the Grab Cut algorithm to improve the efficiency of determining parameters of the GMM.Experimental results show that the proposed algorithm not only has good segmentation effect but also has high segmenta⁃tion accuracy and efficiency.