Back
Semester | spring semester 2020 |
Course frequency | Every spring sem. |
Lecturers | Marcel Lüthi (marcel.luethi@unibas.ch, Assessor) |
Content | Statistical shape models are an important technology in computer vision and medical image analysis. With this technology, the computer learns the characteristic shape variations of an object or organ. The model resulting from this analysis may then be used in implant design, image analysis, surgery planning and many other fields. In this course, we will combine methods from mathematics, statistics and machine learning to build probabilistic models of shape variation. In particular we will formulate shape modelling in a Bayesian setting, using Gaussian processes and Markov-Chain Monte Carlo methods as the core theoretical concepts. We will apply our methods in two real-world projects: The 3D reconstruction of partial bones, and the automatic analysis of femur-bone shapes in 3D CT-images. Both theory and practice are supported by exercises using the open source software Scalismo. This software library is used today in the industry for the automatic detection of organs in medical images or the design of medical implants. |
Learning objectives | At the end of the course the students should be able to - describe how medical images can be analysed using Shape models. - apply the mathematical concept of a Gaussian process to model anatomical shapes - understand Bayesian approaches to medical image analysis - to develop programs for medical image analysis using the open source software scalismo |
Bibliography | Links to related literature will be given as part of the online course. |
Comments | Requires participation in the online course "Shape Modelling - Computing the human anatomy" (www.futurelearn.com/courses/statistical-shape-modelling) |
Weblink | Course Webpage, online course |
Admission requirements | 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++) |
Language of instruction | English |
Use of digital media | Online, mandatory |
Course auditors welcome |
Interval | Weekday | Time | Room |
---|
No dates available. Please contact the lecturer.
Modules |
Doctorate Computer Science: Recommendations (PhD subject: Computer Science) Modul: Concepts of Machine Intelligence (Master's degree subject: Computer Science) Module: Applications of Distributed Systems (Master's Studies: Computer Science) Module: Methods of Machine Intelligence (Master's Studies: Computer Science) |
Assessment format | continuous assessment |
Assessment details | The final grade will be computed based on the result of 2 practical projects and a written exam. Each project contributes 25% to the final grade and the oral exam 50%. Oral exams: 2 July 2020, online. |
Assessment registration/deregistration | Reg.: course registration, dereg: cancel course registration |
Repeat examination | no repeat examination |
Scale | 1-6 0,5 |
Repeated registration | as often as necessary |
Responsible faculty | Faculty of Science, studiendekanat-philnat@unibas.ch |
Offered by | Fachbereich Informatik |