Medicine of the Future: Designing AI Tools for Medical Applications

Course objective:

The goal of the course is to introduce machine learning engineers to the most important principles of working with medical data sets. The course will discuss typical metrics and present ways to deal with the problem of small data sets, image artifacts, and unbalanced classes. The course will include both classic computer vision algorithms and convolutional neural networks.

Who is the target audience?

The course is intended for people with basic knowledge of deep neural networks (e.g. have completed the Introduction to Keras course) and would like to use it in medical data processing. Knowledge of advanced computer vision techniques are not required.

Program:

1. Quality assessment of medical images
2. Typical metrics for classification, detection and segmentation
3. Morphological methods of image processing
4. Removing artifacts from images
5. Image classification using convolutional neural network
6. Segmentation using region growing and superpixel techniques
7. Image segmentation using U-Net network

How to sign up?

1. To register for a course, you need an account in our system. To set it up, click here. This account allows you to use the offer of the entire training platform, including courses conducted by CDSI and other AGH units, which can be accessed using the tabs at the top of the page. If you already have an account, you can skip this step.
2. After creating an account, sign up for the course. Acceptance is based on the order in which applications are submitted.
3. You will receive automatic confirmation of your application from our system, which will include the transfer details.
4. Send payment confirmation to the e-mail address kursy-cdsi@agh.edu.pl.