TeachingSs18MLMI

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

THIS WEBPAGE IS DEPRECATED - please visit our new website

Practical Course:
Machine Learning in Medical Imaging

Prof. Nassir Navab, Shadi Albarqouni, Christoph Baur, Magda Paschali, Huseyin Coskun, Abhijit Guha-Roy, Anees Kazi, Roger Soberanis

Type: Master Practical Course Module IN2106
SWS: 6
ECTS: 10 Credits
Location: CAMP Seminar Room, 03.13.010
Time: Tuesday, 10-12
Course Language: English

Announcements:

  • 03-05-2018: There is no Intermediate Presentation I Session. We will have one Intermediate Presentation on 19th June 2018.
  • 09-04-2018: Projects are assigned! Please contact your tutor by this week to define a regular weekly meeting.
  • 03-04-2018: Projects are announced! Pleaae send us your preferences (at least three preferences) by email to shadi.albarqouni@tum.de by Friday, April 5th. Please make sure the subject of your email is "MLMI_Projects_Preferences". Otherwise, it won't be considered.
  • 29-01-2018: Registration, through TUM Matching Platform, should be done between 09.02. to 14.02.18
  • 13-01-2018: An introductory meeting: Monday, 29.01.2018 (10:00-11:00) in CAMP Seminar Room, 03.13.010.
  • 13-01-2018: Website is up!

About the Course

The aim of the course is to provide the students with notions about various machine learning techniques. The course is subdivided in a lecture/excercises block and a project.

  • The lectures will include topics in image processing and analysis, unsupervised methods, and supervised methods. Each lecture will be followed by a practical hands-on exercise (e.g. 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. The projects are to be realized in couples. The programming language for the projects is to be decided in agreement with your supervisor.

Registration

  • Interested students should attend the introductory meeting to enlist in the course.
  • Students can only register through TUM Matching Platform themselves if the maximum number of participants hasn't been reached (please pay attention to the Deadlines).
  • A maximum number of participants: 20.

Requirements

  • Strong knowledge of Python, MATLAB or another programming language
  • Background in image processing
  • Exercises will be held in preferably in Python, although an introductory lecture on Python will be given previous knowledge would be advantageous.
  • Basic knowledge of C++ is advantageous (in case you decide to use c++ for your final project): knowledge of main concepts of object-oriented programming, basic software engineering, image processing libraries and linear algebra libraries.
  • Basic knowledge of naive machine learning methods and terminology: knowledge of the meaning of the words classification, regression, data-set, cross-validation ...

Schedule

Date Topic By Slides Homework
29.01.2018 Preliminary Meeting (Intro. to ML) Shadi slides
 
10.04.2018 Dimensionality Reduction and Clustering Anees slides1
slides2
Exercise
17.04.2018 Logistic, Linear Regression, and Support Vector Machine Roger slides Exercise
08.05.2018 Random Forests Magda slides Exercise
15.05.2018 Intermediate Presentations I (tentative)<\s> all tutors    
29.05.2018 Neural Networks (NN) and Auto-Encoders (AE) Abhijit slides Exercise (Save Link As...)
05.06.2018 Convolutional Neural Networks Shadi slides Exercise
12.06.2018 Recurrent Neural Networks (RNN/LSTM) Husseyin slides Exercise
19.06.2018 Intermediate Presentation all tutors Each group is supposed to present their progress in 15 to 20 mins. followed by 5 mins Q&A.  
26.06.2018 Attestation Test all tutors Agenda  
03.07.2018 Generative Adversarial Networks (GANs) Christoph    
10.07.2018 Final Presentations all tutors    

Evaluation

The grade will be split between weekly exercises associated to each lecture and a final project.
  • The exercises will be evaluated during a mid-term attestation. The impact of the exercises on the final grade is 30%.
  • The evaluation of the projects will include a final presentation. The impact of the final project on the final grade is 70%.
  • Presentation: Use the CAMP templates for PowerPoint camp-tum-jhu-slides.zip, or Latex: CAMP-latex-template.

Projects

ID Project Tutor Group I Group II Material
1 Retinal OCT Layer Segmentation on Large Scale Bio-marker Analysis Abhijit Fatima, Gonzales Jahnen, Massalimova Project Description
2 Comparison of Graph Convolutional Network and Convolutions neural Networks for fracture detection Anees Zubair, Walter Pai, Nawalgaria Project Description
3 ISIC 2018 Skin Image Analysis Challenge Christoph Rana, Gurudeep Karabulut, Farag Project Description
4 Grand Challenge on Breast Cancer Histology Images Magda Shouman, Hase Gopal, Arumugaswamy Project Description
5 Pancreas Segmentation in Abdominal CT Scans Roger El Husseini, Ghazaei Rickmann, Mejia De Miguel Project Description




TeachingForm
Title: Machine Learning in Medical Imaging
Professor: Prof. Nassir Navab
Tutors: Shadi Albarqouni, Christoph Baur, Magda Paschali, Huseyin Coskun, Abhijit Guha-Roy, Anees Kazi, Roger Soberanis
Type: Praktikum
Information: IN2106, IN8902
Term: 2018SoSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.28 - 22 Jun 2018 - 15:24 - ShadiAlbarqouni

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