Bioimage Informatics

Course Number: 02-740

With the rapid advance of bioimaging techniques and fast accumulation of bioimage data, computational bioimage analysis and modeling are playing an increasingly important role in understanding of complex biological systems. The goals of this course are to provide students with the ability to understand a broad set of practical and cutting-edge computational techniques to extract knowledge from bioimages. Such techniques include image filtering, image feature detection, image classification, image segmentation, object detection, object tracking, image retrieval, image mining and image modeling using both traditional and deep learning methods. Upon successful completion of this course, the student will be able to: explain the importance and understand the principles and uses of both geometrical and machine learning-based bioimage analysis techniques; understand how these techniques can be combined for various applications; develop code to implement basic techniques; and solve specific bioimage analysis tasks using image-processing libraries. Coursework will include homework, two in-class examinations, and doing an independent project on a practical bioimaging problem. Students are expected to have some experience with programming in python.

Key Topics: Image filtering, image feature detection, image classification, image segmentation, object detection, object tracking, image retrieval, image mining and image modeling using both traditional and deep learning methods.

Course Relevance: 

• First-year Biological Sciences PhD students
• MSCB students
• Computational Biology undergraduate students

Units: 12
Prerequisite(s): Students are expected to have some experience with programming in python.

Textbook(s):

Learning Objectives

With the rapid advance of bioimaging techniques and fast accumulation of bioimage data, computational bioimage analysis and modeling are playing an increasingly important role in understanding of complex biological systems. The goals of this course are to provide students with the ability to understand a broad set of practical and cutting-edge computational techniques to extract knowledge from bioimages.

Upon successful completion of this course, the student will be able to:

• explain the importance and understand the principles and uses of both geometrical and machine learning-based bioimage analysis techniques
• understand how these techniques can be combined for various applications
• develop code to implement basic techniques
• solve specific bioimage analysis tasks using image-processing libraries

Assessment Structure: 

Coursework will include homework, two in-class examinations, and doing an independent project on a practical bioimaging problem.