The course consists of two main components: assignments and main project work. The goal of the assignments is for the students to get familiar with the topic of the project and develop a minimal working example that will serve as the basis of the main project work.

Assignment 1: Introduction to histopathology image analysis

Assignment 2: Neural networks for classification

Assignment 3: Convolutional neural networks for classification

Assignment 4: Transfer learning

Main project: Classification of histological preparations of lymph node tissue

After passing the course, the student is able to:

• Understand the given problem and its clinical context;
• Have insight in setting up a research question that can be quantitatively investigated;
• Understand and apply image analysis algorithm(s) to facilitate this investigation;
• Understand and motivate methodological choices;
• Have insight in planning and documentation of the project progress;
• Have insight in documentation and analysis of the solution and results of investigation.

The assessment will be performed in the following way:

• Work on introductory assignments: 20% of the final grade (4 assignments, 5% per assignment);
• Work on the final project: 80% of the final grade (assessment rubric);
• The final grades will be scaled based on the individual contributions of the students based on the self-assessment report (see the self-assessment assignments in Canvas for more details).

Intermediate feedback will be provided as grades to the submitted assignments and during the regular meetings.

The grading will be done per groups, however, it is possible that individual students get separate grade from the rest of the group (e.g. if they did not sufficiently participate in the work of the group). This will be done based on a self-assessment report (see announcement in Canvas for more details).

The students will receive instruction in the following ways:

• Introductory lectures;
• Contact hours with the project instructors and Teaching assitants for questions, assistance and advice;
• Online discussion (in Canvas, see below).

Course instructors:

• Mitko Veta

Teaching assistants:

• Jurre Weijer
• Marcus Vroemen
• Nadiya Lyakh
• Marijn Borghouts

8DB00 Image acquisition and Processing, and 8DC00 Medical Image Analysis.

The example code for the introductory assignments is written in Python. The students can develop the code for the main project work in Python or a programming environment of their choice.

• Answers and code for the 4 assignments. Each assignment contains a detailed submission checklist.
• Report and code for the final project. The report should be a 4-6 page paper using the IEEE template available here. The 6 page limit is strict, however, additional information can be provided in an appendix.
• Mid-term and final self-assessment reports.
• If you use large language models (such as ChatGPT) in your course work, the self-assessment reports should include a reflection on the use of such tools.

All submissions should be done in Canvas.

The course page in Canvas will be used for submission of the assignments and final project work, scheduling of the introductory lectures and contact hours and announcements. The students are highly encouraged to use the Discussion section in Canvas. All general questions (e.g. issues with setting up the programming environment, error messages etc., general methodology questions) should be posted in the Discussion section in Canvas. The contact hours should only be used for questions specific to own project work.