Computational Surgineering

Overview

This course focuses on exploring the potential of Deep Learning and AI in supporting clinical routine and image-guided interventions. Students will be introduced to real-world challenges in the hospital environment and investigate how AI can assist clinicians in their daily workflow through research-driven prototyping.

Working with experts from the Chair for Computer Aided Medical Procedures (CAMP) at TUM and receiving feedback from clinicians at partner hospitals across Munich, students will explore AI-based approaches tailored to real clinical needs. The focus is on understanding clinical workflows, identifying open research questions, and prototyping proof-of-concept solutions using deep learning methods for medical image analysis and intervention support. The course includes:

Access to lecture videos about important aspects for building clinical prototypes: OR training, Tools and methods for software development for medical image processing and computer-assisted interventions, Introduction to regulatory aspects of medical software development (for students who missed IGS and PMSD lectures)
Visit to OR at the clinical partner’s department
Preliminary presentation
Project development
Weekly/Bi-weekly reviews with tutors (help with bug fixing, administrative stuff, connection to experts)
Prototype demonstration - ideally presented to the doctors - end of the semester

Preliminary meeting slides:

docs.google.com/presentation/d/1QCwjvhATUJ_DzEr_aAG8GKFOGPfLieSZAiZQHKvfPKc/edit

Note: The preliminary meeting is scheduled for Jan 29, 2026 10:00 AM. Please use the following link to join the meeting:

tum-conf.zoom-x.de/j/66252059844

Meeting ID: 662 5205 9844
Passcode: 798070

Preliminary meeting slides: docs.google.com/presentation/d/1pdDfvO-tTZzSO4dLHxbHsygNw_pTEO2whtqXYVLuvM0/edit

Please note that by mistake, the kick-off meeting date was mentioned first week of July, however it will be first week of June.

- Registration must be done through TUM Matching Platform (please pay attention to the Deadlines)
- Your chances to be assigned to the course increase if you give the course a higher rank in your choices.
- The maximum number of participants: 24.

Prerequisites and Registration

Experience in programming, in particular Python are needed. Basics of Medical Imaging (e.g., IN2021, IN2022) and Computer Vision are recommended.

Registration must be done through TUM Matching Platform (please pay attention to the Deadlines)
Your chances to be assigned to the course increase if you give the course a higher rank in your choices.
The maximum number of participants: 24.

Objectives

By completing this course, students will be able to:

Apply selected tools and methods for AI-driven medical image analysis and intervention support
Gain insight into clinical workflows within a specific specialty or department
Identify unmet clinical needs and formulate corresponding AI-based research questions
Define requirements for a clinical AI solution based on real-world observations
Prototype and evaluate a proof-of-concept solution using retrospective data, simulations, or phantoms
Communicate their research process and findings to both technical and clinical audiences