Discriminative segmentation of microscopic cellular images

Authors:
Li Cheng;Ning Ye;Weimiao Yu;Andre Cheah
Affiliations:
BioInformatics Institute, A*STAR, Singapore;BioInformatics Institute, A*STAR, Singapore;Institute of Molecular and Cell Biology, A*STAR, Singapore;NUHS, Singapore
Venue:
MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Year:
2011

Citing 8
Cited 1

Edge Detection and Ridge Detection with Automatic Scale Selection

International Journal of Computer Vision
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Large Margin Methods for Structured and Interdependent Output Variables

The Journal of Machine Learning Research
Graphical Models for Structured Classification, with an Application to Interpreting Images of Protein Subcellular Location Patterns

The Journal of Machine Learning Research
Automated Arabidopsis plant root cell segmentation based on SVM classification and region merging

Computers in Biology and Medicine
TurboPixels: Fast Superpixels Using Geometric Flows

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Pascal Visual Object Classes (VOC) Challenge

International Journal of Computer Vision
Cooperation of color pixel classification schemes and color watershed: a study for microscopic images

IEEE Transactions on Image Processing

Context enhanced graphical model for object localization in medical images

MCV'12 Proceedings of the Second international conference on Medical Computer Vision: recognition techniques and applications in medical imaging

Quantified Score

Hi-index	0.00

Visualization

Abstract

Microscopic cellular images segmentation has become an important routine procedure in modern biological research, due to the rapid advancement of fluorescence probes and robotic microscopes in recent years. In this paper we advocate a discriminative learning approach for cellular image segmentation. In particular, three new features are proposed to capture the appearance, shape and context information, respectively. Experiments are conducted on three different cellular image datasets. Despite the significant disparity among these datasets, the proposed approach is demonstrated to perform reasonably well. As expected, for a particular dataset, some features turn out to be more suitable than others. Interestingly, we observe that a further gain can often be obtained on top of using the "good" features, by also retaining those features that perform poorly. This might be due to the complementary nature of these features, as well as the capacity of our approach to better integrate and exploit different sources of information.