Adaptive Automatic Segmentation of HEp-2 Cells in Indirect Immunofluorescence Images

Author

Huang, Yu-Len ; Jao, Yu-Lang ; Hsieh, Tsu-Yi ; Chung, Chia-Wei

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Tunghai Univ., Taichung

fYear

2008

fDate

11-13 June 2008

Firstpage

418

Lastpage

422

Abstract

Indirect immunofluorescence (IIF) with HEp-2 cells is used for the detection of antinuclear autoantibodies (ANA) in systemic autoimmune diseases. An automatic inspection system for ANA testing can be divided into HEp-2 cell detection, fluorescence pattern classification and computer aided diagnosis phases. This study focused on the first phase of cell detecting and locating. This study presented an adaptive edged- based segmentation method for automatically detecting outlines of fluorescence cells in IIF images. The proposed method evaluated 2573 cells with six distinct fluorescence patterns from 45 images. The results of computer simulations revealed that the proposed method always identified cell outlines as were obtained by manual sketched. Such a method provides robust and fast automatic segmentation of HEp-2 fluorescent patterns in ANA testing.

Keywords

diseases; image classification; image segmentation; medical image processing; patient diagnosis; HEp-2 cells; adaptive automatic segmentation; antinuclear autoantibodies; autoimmune diseases; automatic inspection system; computer aided diagnosis phases; fluorescence pattern classification; indirect immunofluorescence images; Automatic testing; Computer simulation; Diseases; Fluorescence; Image edge detection; Image segmentation; Inspection; Pattern classification; Phase detection; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Sensor Networks, Ubiquitous and Trustworthy Computing, 2008. SUTC '08. IEEE International Conference on

Conference_Location

Taichung

Print_ISBN

978-0-7695-3158-8

Electronic_ISBN

978-0-7695-3158-8

Type

conf

DOI

10.1109/SUTC.2008.73

Filename

4545795