Practical Course:
Machine Learning in Medical Imaging

Nassir Navab, Tingying Peng, Diana Mateus, Sailesh Conjeti, Abhijit Guha Roy, Anees Kazi

Type: Master Practical Course Module IN2106
SWS: 6
ECTS: 10 Credits
Location: 03.13.10
Time: Wednesdays, 10:00-12:00
Course Language: English

Announcements

• Since the TUM matching is over and we are currently in the selection process, please do not send us any further motivation letter or inquiry this semester. Students who are interested in the course but missed the matching please consider to participate in the course next semester.
• Due to the large number of enquiry emails, we are not able to answer all of them. If you would like to register the course, please use TUM matching system, and send a motivation email titled as MLMI motivation plus your name (we will use MLMI motivation as a keyword for email search, so emails with other titles will be automatically ignored), and the content of the letter should be put in the email itself. Please do not attach any additional document like word or pdf, and the letter should be less than 200 words. Due to the limited number of positions, we cannot guarantee a position for every highly-motivated student, so please also consider register the course next semester.
• Registration is open from 03.02.2017 to 08.02.2017 through the TUM Matching Platform.
• The preliminary meeting will take place on 25th of Jan at 11:00 a.m. Seminar room 03.13.10
• Lectures and assignments are password protected
• To register for the course, please use the TUM-Matching-System

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 in the beginning of the semester. Each topic will be supervised by a different person. The projects are to be realised in couples. The programming language for the projects is to be decided in agreement with your supervisor.

Schedule

Date	Topic	By	Slides	Homework
25.01.2017	Introduction meeting	Tingying Peng	LabcourseInfo
26.04.2017	Introduction to Python	Marco Esposito	Slides
03.05.2017	Introduction to machine learning and linear classification	Tingying Peng	Slides	Exercise
17.05.2017	Support Vector Machines	Diana Mateus	Slides	Exercise Two moons Digits Dataset
31.05.2017	Random Forests	Sailesh Conjeti	Slides	Exercise and Data
07.06.2017	Deep Learning	Christian Rupprecht	Slides	Exercise
14.06.2017	Dimensionality reduction and clustering	Anees Kazi	Slides Slides	Exercise Data
21.06.2017	Neural Networks and Autoencoders	Abhijit Guharoy	Slides	Exercise and Data
28.06.2017	Attestation	All tutors	Timetable
26.07.2017	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 evaluation of the projects will include a final presentation

Projects

ID	Project	Tutor	Assigned Student	Material
1	Mitochondrial quantification using USK-net	Tingying Peng	Toker Aysim, Savran Yusuf	Mitochondrial Quantification
2	Visualise cell fate choice using dimensional reduction	Tingying Peng	Rui Xu, Marilia de Almeida Lirio	Cell fate visualisation
3	Nuclear segmentation in TEM images	Julien Pontabry	Timo Löhr, Luis Hopf	Nuclear Segmentation
4	Understanding Spatial Transformer Network (STN) for Classification: Group I	Anees Kazi		STN1
5	Understanding Spatial Transformer Network (STN) for Classification: Group II	Anees Kazi	Mustafa Haha Kocyigit, Haha Emre	STN2
6	Detection of abnormality in gastroscopic Images	Sailesh Conjeti	Laven Kewlani, Amit Pandita	EndoVisChallenge I MICCAI 2015
7	Early Barrett's cancer detection	Sailesh Conjeti	Vaheh Hatami, Shoaib Khan	EndoVisChallenge II MICCAI 2015
8	Predicting Survival of Liver Tumor Patients with Machine Learning	Florian Ettlinger	Vivek Sethia, Maida Bakovic, Vitaly Nikolaev	Survival Prediction
9	Unsupervised Anomaly Detection in Medical Images using GANs	Christoph Baur	M.Tarek Saban, Wassim Bahaa, Ahmed Ayad	Anomaly Detection using GANs
10	CNN-based Pose Regression for Registration	Mai Bui	Anshul Sharma, Arvind Somasundaram	Pose Regression
11	Infact Brain MRI Segmentation	Abhijit Guha Roy	Agnieszka Tomczak, Ricardo Smits	MICCAI 2017 Challenge
12	Retinal OCT Fluid Segmentation	Abhijit Guha Roy	Nathalia Spier, Santiago Estrada	Grand Challenge

Attestation Schedule

Registration

• Interested students should attend the introductory meeting to enlist in the course.
• Students can only register through TUMOnline themselves if the maximum number of participants hasn't been reached.
• Maximum number of participants: 20.

Requirements

• *Strong knowledge of MATLAB, Python * or other programment language
• Background in image processing
• Exercises will be held in preferably in Python, althoug 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 Python is advantageous (in case you decide to use python for your final project): numpy, scipy, scikit-learn.
• Basic knowledge of naive machine learning methods and terminology: knowledge of the meaning of the words classification, regression, data-set, cross-validation ...

FAQs