Cetowhite Region Segmentation In Cervix Based On GLCM Characteristic And Level Set Algorithm

Naked eye acetic acid test is an important means of cervical cancer screening,so that the automatic identification of the white area in the colposcopy equipment is an effective way to solve the problem of lack of experienced doctors in clinic.Aiming at this purpose,an improved CV model level set algorithm based on gray level cooccurrence characteristic matrix was developed in this thesis.In this thesis,the segmentation of vinegar and white region is divided into three parts:Firstly,to better distinguish the cervical region from the background region,this thesis made the cervical region of the original pretreatment,mainly using k-means clustering segmentation method using cervical region and gray level ratio from the original image of the cervix in the removal of acetate eye reflex.Secondly,then the acetowhite pictures show the characteristic graphs of different characteristics by using the window function to each characteristic quantity of the gray level co-occurrence matrix.Through a large number of experiments and observing each feature graph to obtain the best feature quantity as the synthesized gray level symbiosis feature quantity,the cervix region has the most obvious characteristics of vinegar whiteness.Therefore,the feature map to be segmented is obtained through feature extraction and ratio extraction.Lastly,a modified CV model level set algorithm was used to segment the feature image and the AW region was obtained eventually.The experimental results on 30 sets of data show that the modified level set algorithm gains an average 26.6% lower sensitivity and an average 29.45% higher specificity comparing with the original CV model level set algorithm.It also gains an average 47.6% higher sensitivity and an average 11.64% lower specificity comparing with watershed algorithm.And an average 11.23% higher sensitivity and an average 45.23% higher specificity comparing with fuzzy clustering algorithm.However,the developed method has an average 19.74%,an average 38.11% an average higher JI(Jaccard Index)accuracy separately comparing with the three aforementioned algorithm.It can be concluded from the results that the new method developed in this paper is a more accurate algorithm in the overall performance.