Title :
A parametric fitting algorithm for segmentation of cell images
Author :
Wu, Hai-Shan ; Barba, Joseph ; Gil, Joan
Author_Institution :
Dept. of Pathology, Mount Sinai Sch. of Med., New York, NY, USA
fDate :
3/1/1998 12:00:00 AM
Abstract :
This paper presents a parametric fitting algorithm for segmentation of cervical and breast cell images from cytology smears. A parametric elliptical model for cells is introduced and the parameters adjusted to fit the cell shapes while minimizing a cost function. Segmentation results of noisy human cervical cell and textured breast cell images demonstrate that the proposed parametric fitting algorithm is very successful in segmentation of images of both nonoverlapped and overlapped elliptically shaped cells.
Keywords :
cellular biophysics; image segmentation; medical image processing; optical microscopy; biomedical image processing; cell images segmentation; cost function minimization; cytology smears; medical diagnostic imaging; noisy human cervical cell images; nonoverlapped elliptically shaped cells; overlapped elliptically shaped cells; parametric elliptical model; parametric fitting algorithm; quantitative pathology; textured breast cell images; Biomedical imaging; Breast; Clustering algorithms; Gas insulated transmission lines; Humans; Image edge detection; Image segmentation; Noise shaping; Pathology; Shape; Algorithms; Breast; Cervix Uteri; Female; Humans; Image Interpretation, Computer-Assisted; Image Processing, Computer-Assisted; Linear Models; Microscopy; Models, Biological; Models, Statistical; Reference Values;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
