Moses - Machine Learning in Medical Image Processing

Display language

Diese Modulbeschreibung gilt nicht im aktuellen Semester.

Die Modulbeschreibung gilt nur für den Zeitraum SS 2018 - WiSe 2022/23. Die Version für das aktuelle Semester (SoSe 2024) finden Sie hier: Modulbeschreibung des SoSe 2024

Module / Version:
#40898 / #1

Validity:
SS 2018 - WiSe 2022/23

Default display language:
English

Module title:
Machine Learning in Medical Image Processing

Credits:
9

Responsible person:
Hennemuth, Anja

Grading:
benotet

Type of exam:
Portfolioprüfung

Zugehörigkeit

Faculty:
Fakultät IV

Institute:
Institut für Technische Informatik und Mikroelektronik

Area of expertise:
34341600 FG Computer Vision and Remote Sensing

Prüfungsausschuss:
No information

Kontakt

Office:
MAR 6-5

Contact person:
Hennemuth, Anja

E-mail address:
anja.hennemuth@campus.tu-berlin.de

Website:

https://icm.charite.de/

Learning Outcomes

Participants will learn how to apply machine learning approaches such as support vector machines and deep learning for the automatic segmentation of medical image data.

Content

Clinical questions in image-based bloodflow analysis, requirement analysis based on a clinical application scenario, 4D image data preparation for machine learning, comparison and validation of image segmentation methods.

Module Components

Pflichtgruppe:

All Courses are mandatory.

Course Name	Type	Number	Cycle	Language	SWS	VZ
Machine Learning in Medical Image Processing	PJ		SoSe	No information	6

Workload and Credit Points

Machine Learning in Medical Image Processing (PJ):

Workload description	Multiplier	Hours	Total
Attendance	15.0	6.0h	90.0h
Pre/post processing	15.0	12.0h	180.0h
			270.0h(~9 LP)

The Workload of the module sums up to 270.0 Hours. Therefore the module contains 9 Credits.

Description of Teaching and Learning Methods

In this project participants will work with MRI datasets typically acquired for the examination of bloodflow in the main artery. The goal is to implement and compare different machine learning approaches for the segmentation of these datasets. The sessions will consist of interleaved theoretical and practical tasks. The theoretical sessions will be dedicated to the introduction of the methods to apply for requirement analysis, data preprocessing, machine learning, validation and result presentation. In the practical sessions these methods will be applied to compile a concept for a clinical image analysis application, as well as an implementation and comparison of different machine learning approaches.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Knowledge about image processing and machine learning techniques is helpful but not mandatory.

Mandatory requirements for the module test application:

This module has no requirements.

Module completion

Grading

graded

Type of exam

Portfolio examination

Type of portfolio examination

100 Punkte insgesamt

Language

German/English

Test elements

Name	Points	Categorie	Duration/Extent
Demonstration of the implemented solutions	30	practical	No information
Presentation of the requirement analysis and the implementation concept (talk)	30	oral	No information
Report summarizing implemented approaches and results	40	written	No information

Grading scale

Notenschlüssel »Notenschlüssel 1: Fak IV (1)«

Gesamtpunktzahl	1.0	1.3	1.7	2.0	2.3	2.7	3.0	3.3	3.7	4.0
100.0pt	86.0pt	82.0pt	78.0pt	74.0pt	70.0pt	66.0pt	62.0pt	58.0pt	54.0pt	50.0pt

Test description (Module completion)

The grade is determined according to § 47 (2) AllgStuPO with the grading system 1 of faculty IV. Talk about the requirement analyses and (30P): The assessment of the presentation is based on its content , structure, design and comprehensibility, appropriate responses to questions. Implementation of machine learning solutions (30P): The implemented solution is graded according to effectiveness, code structure documentation and comprehensivenss Final report (40P): The report with the problem description, implemented approach and result presentation is assessed similar as in a paper review. It is expected that the text covers introduction and motivation, description of the methodology, data and results, discussion and conclusions. The criteria for the report assessment are structure, the clarity of the textblocks, the reproduciblity of the approach based on the text.

Duration of the Module

The following number of semesters is estimated for taking and completing the module:
1 Semester.

This module may be commenced in the following semesters:
Sommersemester.

Maximum Number of Participants

The maximum capacity of students is 20.

Registration Procedures

Anmeldung beim Dozenten und Prüfungsamt

Recommended literature
No recommended literature given

Assigned Degree Programs

Semester:

Zeige auch ausgelaufene Studiengänge und StuPOs

This module is used in the following Degree Programs (new System):

	Studiengang / StuPO	StuPOs	Verwendungen	Erste Verwendung	Letzte Verwendung
This module is not used in any degree program.

Miscellaneous

No information

Machine Learning in Medical Image Processing