Segmentation of Neural Stem/Progenitor Cells Nuclei within 3-D Neurospheres

Authors:
Weimiao Yu;Hwee Kuan Lee;Srivats Hariharan;Shvetha Sankaran;Pascal Vallotton;Sohail Ahmed
Affiliations:
Bioinformatics Institute, Singapore 138671;Bioinformatics Institute, Singapore 138671;Institute of Medical Biology, Singapore 138648;Institute of Medical Biology, Singapore 138648;CSIRO Mathematical and Information Sciences, North Ryde, Australia 1670;Institute of Medical Biology, Singapore 138648
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Year:
2009

Citing 12
Cited 1

An Affine Invariant Interest Point Detector

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Fast Radial Symmetry for Detecting Points of Interest

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Segmentation of Overlapping Nuclei with High Background Variation Using Robust Estimation and Flexible Contour Models

ICIAP '03 Proceedings of the 12th International Conference on Image Analysis and Processing
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Level Set Segmentation of Cellular Images Based on Topological Dependence

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Identification of Cell Nucleus Using a Mumford-Shah Ellipse Detector

ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Level set methods for watershed image segmentation

SSVM'07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision
Geometric approach to segmentation and protein localization in cell cultured assays

ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
3D segmentation of mammospheres for localization studies

ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part I
Combined segmentation and tracking of neural stem-cells

SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis
Automatic Segmentation of High-Throughput RNAi Fluorescent Cellular Images

IEEE Transactions on Information Technology in Biomedicine
Self-Repelling Snakes for Topology-Preserving Segmentation Models

IEEE Transactions on Image Processing

Systems of neuron image recognition for solving problems of automated diagnoses of neurodegenerative diseases

Pattern Recognition and Image Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural stem cells derived from both embryonic and adult brain can be cultured as neurospheres; a free floating 3-D aggregate of cells. Neurospheres represent a heterogenous mix of cells including neural stem and progenitor cells. In order to investigate the self-renewal, growth and differentiation of cells within neurospheres, it is crucial that individual nuclei are accurately identified using image segmentation. Hence effective segmentation algorithm is indispensible for microscopy based neural stem cell studies. In this paper, we present a seed finding approach in scale space to identify the center of nuclei in 3-D. Then we present a novel segmentation approach, called "Evolving Generalized Voronoi Diagram", which uses the identified centers to segment nuclei in neurospheres. Comparison of our computational results to mannually annotated ground truth demonstrates that the proposed approach is an efficient and accurate segmentation approach for 3-D neurospheres.