About the imagedeep.io Coursework:

***

Note: This syllabus is written with the University of Washington radiology resident in mind, and assumes you are enrolled in the on-site Deep Learning Pathway. For remote learners, feel free to explore the course outline below to guide your own studies.

***

If you want to utilize cutting-edge machine learning principles in your medical imaging research, this 6 month immersive experience will help guide you. Deep learning is emerging as a highly promising class of machine learning techniques that allows physicians and engineers to tackle clinical problems that were computationally infeasible just a few years ago. These deep learning methods will likely set a new standard in imaging research going forward, and those who are equipped to utilize them will be highly sought after.

In this pathway, you will learn the foundations of deep learning within the domain of medical imaging. Please survey the course outline below to gain a broad outline of the covered material. When you finish, you will:

-Understand how to frame clinical problems as machine learning tasks

-Learn to build and train neural networks

-Learn to lead successful machine learning projects as a clinical domain expert

-Apply your knowledge by forming a deep learning team and completing a deep learning project from beginning to end

The pathway learning material is divided into subcomponents (see below). Adjunct coursework and resources are provided through the Coursera and DataCamp platforms, and are rigorous, comprehensive, and engaging.

The required coursework is as follows:

There are additional biweekly pass/fail assignments and monthly small-group PBL sessions which will guide you along the coursework. Upon completion of the coursework and a capstone project, a certificate is awarded by the UW Department of Radiology to indicate mastery of both the theory of deep learning and its practical application in the clinical realm.

Course Outline

Month

Week

Material Covered

Assignment

1

1

Deep Learning and Neural Networks

1

3

Computer Vision and Natural Language Processing

2

2

5

Communicating with Technical Teammates

3

7

Defining the Clinical Need

4

3

9

Data Acquisition and Labeling

5

11

Train Your Model

6

4

13

Improve Your Model

7

15

Evaluate Your Model

8

5

17

Clinical Translation: Deploying Models and Regulatory Considerations

9

19

Surveying Startups

10

6

21

Capstone Project Wrap-up  

23

Capstone Project Showcase