Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Predicting Segmentation Accuracy for Biological Cell Images



Adele P. Peskin, Alden A. Dima, Joe Chalfoun


We have performed image segmentations on a very large number of images, using a wide variety of imaging conditions and cell lines, in order to study trends in the segmentation results and make predictions about segmentation accuracy. Comparing results from approximately 40,000 cells, we find a linear relationship between the highest segmentation accuracy seen for a given cell and the fraction of pixels that lie along the edge of that cell, the fraction at risk for error using any method when cells are segmented.
Proceedings Title
6th International Symposium on Visual Computing 2010
Conference Dates
November 29-December 1, 2010
Conference Location
Las Vegas, NV


accuracy, gradients, segmentation


Peskin, A. , Dima, A. and Chalfoun, J. (2010), Predicting Segmentation Accuracy for Biological Cell Images, 6th International Symposium on Visual Computing 2010, Las Vegas, NV, [online], (Accessed June 16, 2024)


If you have any questions about this publication or are having problems accessing it, please contact

Created November 29, 2010, Updated February 19, 2017