Automatic Analysis of Monolayer Cell Cultures using Image Processing methods

 

Overview

Scratch assays are a widely used method in the development of pharmaceuticals. It consists of creating a ‘wound’ in a highconfluence monolayer cell culture, adding a substance to the culture and tracking its effects by observing the closure of the ‘wound’. This closure is affected both by cell migration (movement) and by cell proliferation (mitosis).

Due to the large amount of cells and the short duration of the mitosis event, it is extremely difficult to track cell proliferation manually. An automatic algorithm to track cell mitosis is developed.

A cell undergoing mitosis becomes rounder and brighter. These bright spots are detected in each frame, patches are extracted around them, features are extracted from the spots and the patches in each frame and combined into temporal sequences that describe the event over time, in several frames. The sequences are then classified and the mitosis events in the entire assay are detected. The effect of different substances on cell mitosis rate (proliferation rate) has a great added value in developing cancer treatments and wound healing substances.

 

Publications

Shkolyar, Anat, et al."Automatic detection of cell divisions (mitosis) in live-imaging microscopy images using Convolutional Neural Networks."

Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE. IEEE, 2015.ž

 

horizontal rule

For problems or questions regarding this web page contact hayit@eng.tau.ac.il.
Last updated: 26/11/2015.