Instructors: Prof. Dr. Nassir Navab, Dr. Shahrooz Faghih Roohi, Ashkan Khakzar, Azade Farshad, Anees Kazi, Yusef Yegane
Registration
- Registration must be done through TUM Matching Platform (please pay attention to the Deadlines)
- In order to increase your priority, please also apply via our own Registration system.
- The maximum number of participants: 20-24.
Announcements
- The preliminary meeting slides can be found here: MLMISS22.pdf
- The preliminary meeting is scheduled for Feb 3, 10:00 (Zoom link is visible on TUMonline in the course description).
- ُُThe lectures and presentations happen in hybrid form (the meeting info will be shared with participants via email).
Introduction
- The aim of the course is to provide the students with notions about various machine learning techniques. The course is subdivided into a lecture/exercises block and a project.
- The lectures will include DL topics relevant to medical imaging applications. Each lecture will be followed by a practical hands-on exercise (e.g. the implementation in Python).
- The topics of the projects will be distributed at the beginning of the semester. Each topic will be supervised by a different person.
Course Structure
In this Master Praktikum (Hauptseminar), students select one scientific article from the list provided by course organizers. The students read the paper, and must accomplish the following:
- Presentation: 50% Intermediate and Final Presentation (Done by all tutors -- mainly on your presentation skill, progress so far compared to other groups ...etc.)
- Use the CAMP templates for PowerPoint camp-tum-jhu-slides.zip
- The guideline for mid-presentation can be found here: Guideline for intermediate presentation (SS2022 MLMI).pdf
- The guideline for the final presentation can be found here: GuidelineMLMI_Final presentation_SS2022.pdf
- Project Progress: 50% Project Progress (Done by your tutor -- mainly on your weekly progress on lrz git repository.
Schedule of Lectures
Date | Session: Topic | Slides | Lecturer |
---|---|---|---|
05/05 | Interpretability | Ashkan Khakzar | |
12/05 | Medical Image Reconstruction | Shahrooz Faghihroohi | |
19/05 | Graph Neural Networks | Anees Kazi | |
02/06 | Transformers | Yousef Yeganeh | |
09/06 | Generative Models | Azade Farshad | |
23/06 | Midpresentation | Students | |
30/06 | Invited Talk | Thomas Wendler | |
07/07 | Invited Talk | Ghazal Ghazaei | |
14/07 | Semi-Supervised Methods | Tariq Bdair | |
21/07 | Incremental learning | Indu Joshi | |
28/07 | Final Presentation | Students |
Projects
Project | Tutors | Description | FStudents |
---|---|---|---|
Explaining Medical Image Classifiers with Visual Question Answering Models | MLMI_SoSe22_VQA Models.pdf | Fabian Scherer, Andrei Mancu, Alaeddine Mellouli, Çağhan Köksal | |
Structured report generation | MLMI_SoSe22_Structured Report Generation.pdf | Yiheng Xiong, Jingsong Liu. Priyank Upadhya, Melis Gülenay | |
A comprehensive study of Semi-Supervised Learning in Medical Imaging | Tariq Bdair | MLMI_SoSe22_SemiSupervisedLearning.pdf | Mert Sayar, Anna Banaszak, Cenk Eralp, Umaid BIn Zubair |
SceneGenie: Scene Graph to Image via CLIP Embeddings and Diffusion Model-based Generation | MLMI_SoSe22_SceneGenie.pdf | Chengzhi Shen, Yu Chi, Jacopo Sitran, Tobias Vitt | |
Exploring generative models for OCT Image generation | MLMI_SoSe22_OCT Image Generation.pdf | Daria Matiunina, Furkan Çelik, Sebastian Richstein, Murilo Bellatini | |
GeNoMe: Generating Anomalies in Medical Imaging | MLMI_SoSe22_GeNoMe.pdf | Andrea Matécsa, Jakob Ropers, Yixuan Hu, Ata Jadid Ahari |