Image Segmentation Based on the Local Center of Mass

Version 1.1.2 (7.62 KB) by Iman Aganj
Matlab codes for unsupervised 2D and 3D image segmentation, using a local-center-of-mass approach.
5.0
(1)
1.1K Downloads
Updated 9 Apr 2025

View License

These are codes for unsupervised 2D and 3D image segmentation, using an approach based on the local center of mass of regions, described in:
I. Aganj, M. G. Harisinghani, R. Weissleder, and B. Fischl, “Unsupervised medical image segmentation based on the local center of mass,” Scientific Reports, vol. 8, Article no. 13012, 2018.
www.nature.com/articles/s41598-018-31333-5
See EXAMPLE.m for a short tutorial. If available, a GPU can be used to speed up the segmentation.

Cite As

Iman Aganj (2026). Image Segmentation Based on the Local Center of Mass (https://www.mathworks.com/matlabcentral/fileexchange/68561-image-segmentation-based-on-the-local-center-of-mass), MATLAB Central File Exchange. Retrieved .

I. Aganj, M. G. Harisinghani, R. Weissleder, and B. Fischl, “Unsupervised medical image segmentation based on the local center of mass,” Scientific Reports, vol. 8, Article no. 13012, 2018. www.nature.com/articles/s41598-018-31333-5

MATLAB Release Compatibility
Created with R2018b
Compatible with any release
Platform Compatibility
Windows macOS Linux
Tags Add Tags
Open in new tab
Version Published Release Notes
1.1.2

Minor update.
1.1.1

Minor update.
1.1

In findCMs.m, the dimension through which the center of mass is computed is now adjustable and defaults to 1.
1.0.3

Minor update.
1.0.2

Minor update.
1.0.1

Minor update.
1.0.0