Navigated to

For those who are admitted to

Deep Learning with Applications in Medical Imaging 7.5 credits

Here you will find information for the start of your studies.

Exchange students

Study location: Umeå

Type of studies: On campus

Welcome to your studies!

You have been admitted to Deep Learning with Applications in Medical Imaging, 3RA040 at Umeå University. This page gives you all the information you need before starting your studies. We hope you will learn lots and enjoy your studies at Umeå University.


Checklist for the start of your studies

Before the first day of your education, you need to take some important steps.

1.Your offer

You have been admitted. If you want to keep your place (seat), you do not have to reply to your offer.

If you do not want to keep your place you should decline your offer by logging in to 'My pages' on universityadmissions.se, and follow the instructions. You should click "I wish to decline this offer" next to the course or programme you want to decline.

If you see "Reserve" next to your course or programme in the Notification of selection results, this means that you've been placed on a waiting list for that course/programme.

 

2.Activate your user account and MFA

As a new student, you need to activate your user account (your UMU-id) approximately two weeks prior to the start of the semester.

With your user account you can:

  • register for courses
  • access the internet in computer labs and the university's wireless network
  • submit assignments and verify your study results
  • access your student e-mail

If you are a new student, you will automatically receive a user account when you are admitted, but you will need to activate it for it to function properly. You will not be able to activate it until approximately two weeks prior to the start of the semester.

Exchange student or tuition fee paying student

If you are an exchange student or tuition fee paying student, you will receive an email with instructions on how to activate your account.

Install MFA for a more secure login

To increase security and reduce the risk of unauthorised access to your information or account, students must enable multi-factor authentication (MFA) to log in to various systems, such as Canvas and the Student Web.

I want to activate my user account and install MFA

Help! It´s not working

If you are having problems activating your account or logging in, please contact our Servicedesk. You will find answers to common questions, and can submit enquiries.

 

3.Course registration

For this course you must register in LADOK before the course starts. If you know in advance that you will not be able to register, you must notify us. If you suffer from an acute illness or other unforeseen event that prevents you from registering, you must contact us as soon as possible (a medical certificate is required). 

To register for the course, you must first activate your Umu-id. Please note that the course call is mandatory; it is very important to notify the course coordinator if you are unable to attend.

 

4.Course start

Start date

2026-03-24

Time

13:15

Place

To be updated later

Schedule Go to the schedule for VT2026

The schedule is preliminary until four weeks before the course starts

This course covers deep convolutional neural networks (CNNs) for computer vision, with applications in medical image analysis. The course provides an introduction to basic machine learning concepts, describes neural networks and the field of deep learning, and then delves into deep convolutional networks. The course describes the different parts used to build deep convolutional networks and covers, among others, filters, activation functions, loss functions; regularization techniques such as batch normalization and dropout; explains several of the different nonlinear optimization algorithms used to train the networks, and describes popular network architectures, discussing their advantages and disadvantages.

The course also covers generative models, such as variational autoencoders (VAEs) and generative adversarial networks (GANs).

Students in the course will learn to implement and train modern network architectures and deep learning methods, and to apply these to large image data sets, both on medical images and on other images.

The course includes two modules:

  1. Theory part 5.5 credits
  2. Laboratory part 2.0 credits

All communication with the students during the course takes place via Canvas. When you have registered for the course (see above), you will have access to the course information on Canvas. It is important that you take note of this information; if you do not use your university email account, it is important that you arrange for it to be forwarded to another email address.

The course you are going to take is given by the Department of Diagnostics and Intervention.

Course coordinator

Study administrator

Contact us

Please be aware that the University is a public authority and that what you write here can be included in an official document. Therefore, be careful if you are writing about sensitive or personal matters in this contact form. If you have such an enquiry, please call us instead. All data will be treated in accordance with the General Data Protection Regulation.

New message

More tips for a good start

Two smiling students sitting at an outdoor table on campus.

Welcome to new students

There are some things you need to prepare before your studies start.

A blurred person is walking home among residential buildings in a wintery Umeå.

Accommodation

Support and resources to help you find a place to live in Umeå.

A person holding a cell phone in their hand.

Digital map of Campus Umeå

Digital map with indoor navigation.