Curriculum
  /  
Descriptions
ELEC_ENG 395, 495: Machine Learning for Medical Images and Signals


VIEW ALL COURSE TIMES AND SESSIONS

Description

Prerequisites
ELEC_ENG 375 / 475

Prerequisites
An understanding of the fundamentals of machine learning and image processing. Students will be expected to read papers that utilize advanced machine learning and image processing techniques. Familiarity with one of the major machine-learning software frameworks is required to complete the class project. 

Description
This seminar course will introduce engineering and computer science students to applications of machine learning in biomedical imaging, sensor, and genomic data. Lectures will orient students to application domains and issues in data, algorithm design, and validation and will provide background for paper discussions in areas including radiology, pathology, and critical care. A course project provides hands-on experience designing and validating machine learning models with real-world data. 

OBJECTIVES: Following this course students will be able to:

  1. Describe fundamental machine learning problems in major biomedical application domains
  2. Understand the unique challenges associated with biomedical data in different domains
  3. Describe challenges in validating ML algorithms in healthcare and biomedical research, and formulate rigorous validation protocols
  4. Identify major public databases that can be used to develop and validate ML algorithms 

COURSE COORDINATOR: Lee Cooper
REQUIRED TEXT: None
EVALUATION METHOD: Evaluation will be based on the project and class participation. There are no examinations in this course.