AUTOMATED CELL SEGMENTATION WITH 3D FLUORESCENCE MICROSCOPY IMAGES

被引：0

作者：

Kong, Jun ^{[1
]}

Wang, Fusheng ^{[1
]}

Teodoro, George ^{[2
]}

Liang, Yanhui ^{[1
]}

Zhu, Yangyang ^{[1
]}

Tucker-Burden, Carol ^{[3
]}

Brat, Daniel J. ^{[1
,3
]}

机构：

[1] Emory Univ, Dept Biomed Informat, Atlanta, GA 30322 USA

[2] Univ Brasilia, Dept Comp Sci, Brasilia, DF, Brazil

[3] Emory Univ, Dept Pathol, Atlanta, GA 30322 USA

来源：

2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI) | 2015年

关键词：

Fluorescence Microscopy Image; 3D Cell Analysis; Gradient Vector Flow;

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

A large number of cell-oriented cancer investigations require an effective and reliable cell segmentation method on three dimensional ( 3D) fluorescence microscopic images for quantitative analysis of cell biological properties. In this paper, we present a fully automated cell segmentation method that can detect cells from 3D fluorescence microscopic images. Enlightened by fluorescence imaging techniques, we regulated the image gradient field by gradient vector flow ( GVF) with interpolated and smoothed data volume, and grouped voxels based on gradient modes identified by tracking GVF field. Adaptive thresholding was then applied to voxels associated with the same gradient mode where voxel intensities were enhanced by a multiscale cell filter. We applied the method to a large volume of 3D fluorescence imaging data of human brain tumor cells with ( 1) small cell false detection and missing rates for individual cells; and ( 2) trivial over and under segmentation incidences for clustered cells. Additionally, the concordance of cell morphometry structure between automated and manual segmentation was encouraging. These results suggest a promising 3D cell segmentation method applicable to cancer studies.

引用

页码：1212 / 1215

页数：4