The use of AI in healthcare is expanding and can be used with image data, such as X-ray, MRI and other medical images. This intermediate level module aims to equip you with foundational knowledge and practical coding and engineering skills to ensure that you feel confident applying deep learning to real world health care problems and adapting to the fast paced field as it moves forward in future.

This module is for you if:

• Are interested in applying deep learning and AI to healthcare images.
• Wanting to expand your current knowledge of AI
• Already have a working knowledge of Python including classes and can use packages such as numpy.
• Have an understanding of mathematical concepts such as first order partial derivates and matrix algebra.

Course delivery mode:
This module is taught over nine session with a mixture of video lectures, quizzes and practicals. At various points in this module you are required to attempt a short interactive Quiz. You must answer all the questions correctly before you will be able to move on to the next part of the module; however you can have as many attempts at each quiz as you need. This is to help you implement your learning and be sure you fully understood each session before moving on. When you pass the final quiz, you will be able to download a completion certificate.

Learning aims:
On completion of this module you will :

• Be able to implement simple fully connected networks from scratch in Python. and common deep networks in PyTorch.
• Be exposed to a wide range of deep learning applications for healthcare and be comfortable applying the ideas raised in the module to your own research.
• Understand the strengths and limitations of deep learning and how to adapt modern networks to work on challenging real-world medical imaging data.
• Understand how to validate models effectively and troubleshoot problems with their architectures.

Technology required:
We will be using Jupyter Notebooks created for you to run on Google Colabatory (Colab). Full details on accessing Colab are given in the Get Started section of this module