Computational Analysis of Heterogeneity of Cellular Images

Cellular heterogeneity has become an increasingly important topic in many areas of cell biology on a wide range of spatiotemporal scales. This course will introduce important concepts of computational image analysis and machine learning that help us characterize cellular heterogeneity within cell images. After the formal lectures, we will utilize the standard software such as MATLAB, CellProfiler, ImageJ in hands-on experiences. The topics will include image processing, segmentation, tracking, feature extraction, and machine learning (supervised and unsupervised). Sample images will be provided, but students are also encouraged to bring their own data for the hands-on analysis if they have it. Previous basic coding or ImageJ experience will be helpful even though it is not required.

Course Learning Objectives

• Understand and apply image analysis algorithms to extract quantitative information from cellular images
• Understand and apply machine learning algorithms to analyze the heterogeneity of cellular images

Enrollment

This course is designed for up to 20 participants. Enrollment over 20 will be considered on a case-by-case basis.

Session Dates and Times

Priority will be given to graduate students taking the course for credit. In order to receive credit, students must attend all sessions and complete all assignments. Postdocs can register, too and they will be granted access to the course as space allows. The course will take place in person.

Session One: January 9, 2023 1:00 pm to 2:30 pm
Session Two: January 10, 2023 1:00 pm to 2:30 pm
Session Three: January 11, 2023 1:00 pm to 2:30 pm
Session Four: January 12, 2023 1:00 pm to 2:30 pm

Session Location

TMEC Room 128