Machine Learning for Cell Image Analysis


The development of modern bright field microscopes especially time-lapse image sequences contain information about the dynamics of cells, the distribution of subcellular components, and the activity of molecules allows more detailed investigations of the cell activities. However, it also brings challenges for automatic cell image analysis because of the low-contrast nature of bright field microscopic images.

In this project we seek for machine learning models and algorithms to provide more accurate and robust results for cell segmentation and spot detection.

Students joining this project are invited to work in the following areas:

• Supervised Learning, e.g. using SVM

• Low-Rank Matrix Recovery and Completion, e.g.

• Robust PCA

• Graphical Model

• Bayesian Estimation


Sikun Yang

Francois-Xavier Lehr