Related Experiment Video
Updated: Apr 15, 2026
05:33
Three-Dimensional Shape Modeling and Analysis of Brain Structures
Published on: November 14, 2019
7.7K
Graph-regularized 3D shape reconstruction from highly anisotropic and noisy images.
Christian Widmer1, Stephanie Heinrich2, Philipp Drewe1
1Sloan Kettering Institute, 1275 York avenue, New York, NY, USA.
Signal, Image and Video Processing
|April 14, 2015
Summary
This study introduces an automated tool for segmenting cellular nuclei in 3D microscopy images. The new method matches manual accuracy while significantly reducing processing time for biological experiments.
Area of Science:
- Biomedical Imaging
- Cell Biology
- Computational Biology
Background:
- Accurate cellular nuclear segmentation is crucial for understanding biological processes.
- Manual segmentation of nuclei in 3D microscopy data is time-consuming and a bottleneck for large-scale studies.
- Challenges include anisotropic and noisy 3D image data.
Purpose of the Study:
- To develop an automated tool for segmenting cellular nuclei from 3D fluorescent microscopic data.
- To provide a user-friendly interface for researchers.
- To improve the efficiency of analyzing large biological datasets.
Main Methods:
- Utilized state-of-the-art image processing techniques.
- Applied advanced machine learning algorithms.
- Developed a graphical user interface for ease of use.
Main Results:
- The automated tool achieved accuracy comparable to manual annotation.
- Demonstrated a significant reduction in the time required for nuclear segmentation.
- Successfully processed challenging 3D anisotropic and noisy image data.
Conclusions:
- The developed tool offers an efficient and accurate solution for cellular nuclear segmentation.
- Automating this process overcomes a major bottleneck in large-scale biological research.
- The user-friendly interface facilitates broader adoption in microscopy image analysis.
