Probabilistic Morphable Models
-

Online course and Summer school

Online Course
Feb. 17th - April 12th on FutureLearn

Summer school
Postponed to unknown date due to Corona Virus

Course overview


Probabilistic Morphable Models

Probabilistic Morphable Models are a fully probabilistic approach to model-based image analysis, based on:

  • the theory of Gaussian processes for modelling shapes
  • Markov chain Monte Carlo (MCMC) methods for model fitting
  • a software framework for efficient development of image analysis solutions.

This course teaches the theoretical basis of shape modelling and model fitting and provides an introduction on how to use the software framework Scalismo. The participants will apply the learned concepts and methods in a course project, whose goal it is to develop an interactive, model-based segmentation application.

Course organization

The course consists of two parts: An open online course and a summer school.

In the online course, participants learn the basic theory of shape modelling and are given a practical introduction to Scalismo. Participants of this course, who submit a solution to the course project, are invited to attend the summer school.

The summer school will focus on model-based image analysis. In theory lectures, participants will learn more about model-fitting and registration, with particular emphasis on probabilistic model-fitting using Markov Chain Monte Carlo methods. An important part of the summer-school is the course project. The participants will implement a complete application for interactive model-based segmentation of medical images using the open source framework Scalismo.

Target audience

The intended audience for the course is beginning graduate students and researchers from academia and industry interested in shape and image analysis.

Prerequisite is knowledge of basic probability theory and statistics as well as linear algebra. Participants should have good programming skills in at least one programming language (ideally Java, C++ or Python).

Information


The course will take place at the University of Cape Town. More details will soon follow.

Instructors & Tutors


Thomas Vetter
Thomas Vetter is the founder and head of the Graphics and Vision Research Group of the University of Basel. Thomas Vetter’s research at the University of Basel is directed at automated synthesis and analysis of images.
Thomas Vetter
Marcel Lüthi
Marcel Lüthi is a lecturer at the University of Basel. His research focuses on the use of Gaussian Processes for shape modelling for application in medical image analysis.
Marcel Lüthi
Ghazi Bouabene
Ghazi Bouabene is a previous member of the Graphics and Vision Resarch Group. He is one of the main developers of Scalismo. He is currently CEO of the company Shapemeans, which provides customized software solutions for shape and medical image analysis.
Ghazi Bouabene
Tinashe Mutswangwa
Tinashe Mutswangwa is a Senior Lecturer in biomedical engineering and health innovation with the University of Cape Town. His research projects center on the application of image and image analysis methods for computer-aided diagnosis, spanning topics from 3-D reconstruction of bone, X-ray imaging, statistical shape and appearance modelling and 3D morphometrics.
Tinashe Mutswangwa

Programme


Online course (Feb 2020 - May 2020)

From To Subject
Mon 2/17     Sun 2/23     Basic concepts of shape modelling and the scalismo software.
Mon 2/24 Sun 3/1 Building shape models: fundamental concepts in theory and practice.
Mon 3/2 Sun 3/8 Probabilistic aspects of shape models.
Mon 3/9 Sun 3/15 Modelling with Gaussian Processes
Mon 3/16 Sun 3/22 Reconstructing missing parts
Mon 3/23 Sun 3/29 Fitting models to data
Mon 3/30 Sun 4/5 Model-based image analysis
Mon 4/6 Sun 4/12 Course Project

Tentative programme of the Summer school (June 29 - July 3, 2020)

Day Subject
Mon 6/29 Analysis-by-synthesis and non-rigid registration
Tue 6/30 Bayesian inference and probabilistic model fitting
Wed 7/1 Beyond segmentation: Applications of shape modelling in biomedical image analysis
Thu 7/1 Advanced topics in Gaussian processes and MCMC
Fri 7/3 The computer vision perspective: Automated analysis of 2D face images

Registration


To registration for the online course, please go directly to FutureLearn.

To register for the summer school, please send an e-mail to the address below. Note that the summer school is free of charge, but requires some investment of time from your side. A prerequisite for admission is the successfully completion the course project, which is part of the online course.