Zur Merkliste hinzufügen
Zurück

 

43075-01 - Vorlesung: Probabilistic Shape Modelling 6 KP

Semester Frühjahrsemester 2022
Angebotsmuster Jedes Frühjahrsem.
Dozierende Marcel Lüthi (marcel.luethi@unibas.ch, BeurteilerIn)
Inhalt Statistical shape models are models, which represent the typical variability of an organ or shape in terms of a probability distribution. The most important application of shape models is in medicine, where they are used for the analysis of medical images, surgery planning or the design of implants. There are, however, also many application in other fields, such as bio-mechanics, anthropology or forensics.

In this course the participants will address a classical problem in the forensics sciences using shape modelling: Given a fragment of a bone, what can we say about the person? To solve this mystery, we will combine methods from mathematics, statistics and machine learning. More precisely, the participants will learn about Gaussian processes, Bayesian modelling and Markov Chain Monte Carlo methods. All the mathematical methods will be practically explored and visualized using the open source software library Scalismo.
Lernziele At the end of the course the students should be able to
- describe how shapes can be analyzed using statistics .
- apply the mathematical concept of a Gaussian process to model anatomical shapes
- follow a principled Bayesian workflow for analysing shapes.
- develop programs for medical image analysis using the open source software scalismo
Literatur Links to related literature will be given as part of the course.
Bemerkungen Requires participation in the online course "Shape Modelling - Computing the human anatomy" (www.futurelearn.com/courses/statistical-shape-modelling)
Weblink Course Webpage

 

Teilnahmebedingungen Open to Master and PhD students with basic knowledge in probability theory and statistics, linear algebra as well as programming experience in a modern programming language (e.g. Java or C++)
Unterrichtssprache Englisch
Einsatz digitaler Medien Online-Angebot obligatorisch
HörerInnen willkommen

 

Intervall wöchentlich
Datum 22.02.2022 – 31.05.2022
Zeit Dienstag, 14.15-16.00 Spiegelgasse 5, Seminarraum 05.002
Datum Zeit Raum
Dienstag 22.02.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 01.03.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 08.03.2022 14.15-16.00 Uhr Fasnachtsferien
Dienstag 15.03.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 22.03.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 29.03.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 05.04.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 12.04.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 19.04.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 26.04.2022 14.15-16.00 Uhr Spiegelgasse 1, Seminarraum 00.003
Dienstag 03.05.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 10.05.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 17.05.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 24.05.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Dienstag 31.05.2022 14.15-16.00 Uhr Spiegelgasse 5, Seminarraum 05.002
Module Doktorat Informatik: Empfehlungen (Promotionsfach Informatik)
Modul: Applications of Distributed Systems (Masterstudium: Computer Science)
Modul: Concepts of Machine Intelligence (Master Studienfach Computer Science)
Modul: Methods of Machine Intelligence (Masterstudium: Computer Science)
Leistungsüberprüfung Lehrveranst.-begleitend
Hinweise zur Leistungsüberprüfung The final grade will be computed based on the result of a practical project and a written exam. The project contributes 50% and the written exam 50% to the final grade.
Written exam, expected date: 7 July 2022, 2-4, Spiegelgasse 5, room 05.002.
An-/Abmeldung zur Leistungsüberprüfung An-/Abmelden: Belegen resp. Stornieren der Belegung via MOnA
Wiederholungsprüfung keine Wiederholungsprüfung
Skala 1-6 0,5
Wiederholtes Belegen beliebig wiederholbar
Zuständige Fakultät Philosophisch-Naturwissenschaftliche Fakultät, studiendekanat-philnat@unibas.ch
Anbietende Organisationseinheit Fachbereich Informatik

Zurück