Related Experiment Video
Updated: May 31, 2026
12:08
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
Published on: August 13, 2014
TISSUE LEVEL SEGMENTATION AND TRACKING OF BIOLOGICAL STRUCTURES IN MICROSCOPIC IMAGES BASED ON DENSITY MAPS
K Mosaliganti1, A Gelas, A Gouaillard
1Harvard Medical School, Department of Systems Biology, 200 Longwood Avenue, Boston, MA - 02115, USA.
Summary
This study introduces a novel method for segmenting and tracking dense cell structures in microscopy images. The technique uses a modified Mumford-Shah energy functional to automatically identify and outline cellular formations during embryogenesis.
Area of Science:
- Developmental biology
- Image analysis
- Computational modeling
Background:
- Cellular coordination is crucial during embryogenesis, forming geometric arrangements.
- Early embryonic development involves cell clumps that organize into dense structures.
Purpose of the Study:
- To explore density-based segmentation and tracking of cellular structures in microscopy images.
- To develop a novel variational level-set method for automated cell structure segmentation.
Main Methods:
- Utilized a modified Mumford-Shah energy functional.
- Derived a variational level-set for density-based segmentation.
- Evolved initialized contours on density maps to generate cell structures.
Main Results:
- Successfully segmented and tracked dense cellular structures.
- Demonstrated automated generation of novel cell structures upon convergence.
- Validated the method on confocal ear images of zebrafish embryos.
Conclusions:
- The developed method offers an effective approach for density-based segmentation and tracking of cellular structures.
- This technique aids in understanding cellular organization during embryonic development.
- The approach shows promise for analyzing complex biological patterns in microscopy data.
