Title :
Outline Detection for the HEp-2 Cell in Indirect Immunofluorescence Images Using Watershed Segmentation
Author :
Yu-Len Huang ; Chung, Chia-Wei ; Hsieh, Tsu-Yi ; Jao, Yu-Lang
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Tunghai Univ., Taichung
Abstract :
An automatic inspection system for antinuclear autoantibodies (ANA) testing can be divided into HEp-2 cell detection, fluorescence pattern classification and computer aided diagnosis phases. This paper presented a multi-staged segmentation method for automatically detecting outlines of fluorescence cells in Indirect immunofluorescence (IIF) images. The similarity-based watershed algorithm performed the marker to prevent over-segmentation. This paper evaluated 2305 autoantibody fluorescence patterns with manual sketched outlines (including 456 diffuse patterns, 417 peripheral patterns, 719 coarse speckled patterns, 55 fine speckled patterns, 517 discrete speckled patterns and 141 nucleolar patterns) from 44 IIF images. The experimental results revealed that the proposed method can practically outline fluorescence cells from IIF images.
Keywords :
cellular biophysics; fluorescence; image classification; image segmentation; medical image processing; object detection; HEp-2 cell outline detection; antinuclear autoantibody testing; automatic inspection system; computer aided diagnosis phase; fluorescence pattern classification; immunofluorescence image; multistaged segmentation method; watershed segmentation; Automatic testing; Computer networks; Fluorescence; Image resolution; Image segmentation; Inspection; Microscopy; Pattern classification; Phase detection; System testing;
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
DOI :
10.1109/SUTC.2008.72
