Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Practical Course:
Machine Learning in Medical Imaging

Nassir Navab, Tingying Peng, Lichao Wang, Loic Peter, Benjamin Gutierrez Becker, Shadi Albarqouni, Fausto Milletarì

Type: Master Practical Course Module IN2106
SWS: 6
ECTS: 10 Credits
Location: MI 03.13.010
Time: Tuesday 16:00-17:30
Course Language: English


  • July, 25th: Preliminary meeting is scheduled on 25th of July, 14:00-15:00pm in MI 03.13.010
  • Oct, 29th: Projects have been assigned. Please contact your supervisor as soon as possible to setup an initial meeting.
  • Jan, 8th: Final presentation is scheduled on 27th of Jan 16:00-17:30

About the Course

In this course students will learn through practice the application of different machine learning methods to problems involving medical images. The Master-Praktikum will consist in:

  • (1) a few introductory lectures on machine learning and its application in different problems involving medical imaging,
  • (2) a number of exercises to apply different learning approaches to toy example data,
  • (3) a machine learning project with a real medical application to be solved in groups (pairs).

Regular meetings will be held individually with each group to follow up the progress of the project along the semester


  • Homework attestations (25%)
  • Project (75%), including:
  • Practical implementation
  • Midterm and final Presentations:Use the CAMP templates for PowerPoint CAMPmaster.pot, or Latex: CAMP-latex-template.zip.
  • Report : Maximum 8 pages. Please download and use the llncs2e.zip Latex template.


  • Interested students should attend the introductory meeting to enlist in the course.
  • Students in the waiting list of summer term would have priority for registration.
  • Students can only register through TUMOnline themselves if the maximum number of participants hasn't been reached by end of August.
  • Maximum number of participants: 24.


  • Basic knowledge in MATLAB and C/C++ programming is an advantage.

Preliminary Schedule

Date Topic By Slides Homework
25.07.2014 Introduction Meeting all    
07.10.2014 Image Representation and Feature Extraction Loic Peter Slides Exercise1
14.10.2014 Linear Classifiers and Support Vector Machines (SVMs) Benjamin G Becker Slides Exercise
21.10.2014 Evaluation Measures and Bootstrap Tingying Peng Slides
28.10.2014 Boosting Tingying Peng Slides
04.11.2014 Random Forests Loic Peter Slides Exercise5
11.11.2014 Principal Component Analysis (PCA) and Statistical Shape Models Fausto Milletari Slides Exercise6
18.11.2014 Clustering Lichao Wang Slides Exercise7
25.11.2014 Introduction to Sparse Methods Shadi Albarqouni Slides  
02.12.2014 Attestations All tutors    
09.12.2014 Midterm Presentation All tutors    
27.01.2015 Final Presentation All tutors    

Group Project Supervision
Salvatore Virga, Beatrice Lentes Super resolution using dictionary learning Tingying
Oliver Baptista, Ahsan Ziaullah Context Learning for Label Prediction in Cardiac Magnetic Resonance Images Lichao
Iro Laina, Cristina Precup Estimation of pseudo CT images from MR images Benjamin
Chandra Shekhar Kushwaha, Christoph Baur Supervised Dictionary Learning Shadi
Homa Rasouli, Sara Hajmohammadalitorkabadi Robust Statistical Shape Model using particle based shape analysis Benjamin
Neda Davoudi, Judith Zimmermann MR Image Segmentation using boosting Tingying
Ye Tao, Yuxiang Gong, Sampa Karthikeya Cell Tracking Challenge Fausto
Yaoguang Jia, Richeek Swami, Oliver Etzel Unsupervised domain adaption: geodesic flow kernel and subspace alignment methods Loic

Title: Machine Learning in Medical Imaging
Professor: Prof. Dr. Nassir Navab
Tutors: Tingying Peng, Lichao Wang, Loic Peter,Benjamin Gutierrez Becker, Shadi Nabil Albarqouni, Fausto Milletarì
Type: Praktikum
Information: 10 ECTS credits
Term: 2014WiSe

Edit | Attach | Refresh | Diffs | More | Revision r1.23 - 19 Jan 2015 - 09:55 - TingyingPeng

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif