• University of Basel logo

Statistical Shape Modelling: Computing the Human Anatomy

Learn the technology of modelling, as used in computational face recognition or in surgeries, with this free online course.

6,614 enrolled on this course

Statistical Shape Modelling: Computing the Human Anatomy
  • Duration

    8 weeks
  • Weekly study

    4 hours

Learn modern methods that will help shaping the future of medical interventions

Statistical shape models are one of the most important technologies 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 free online course, you will get insights from mathematics, statistics and machine learning, in order to address practical problems, as well as a theoretical and practical introduction to the open source software Scalismo.

Download video: standard or HD


  • Week 1

    Basic concepts of shape modelling and the Scalismo software

    • Course introduction

      Meet the educators Ghazi Bouabene and Marcel Lüthi, introduce yourself to the other participants, and make your first acquaintance with shape modelling.

    • Shape modelling basics

      What is a shape? How do we measure and model shapes? Learn the basic notions of shape modelling.

    • Introducing the software environment

      Take your first steps with our shape modelling software framework Scalismo.

  • Week 2

    Building shape models: fundamental concepts in theory and practice

    • Modelling shape variations using Gaussian Processes

      We introduce the fundamental concept of Gaussian Processes, discuss how it generalises the multivariate normal distributions, and build a first shape model.

    • Experimenting on a face dataset using Scalismo

      Learn how to prepare a dataset for shape modelling and experience in code the relation between shape models and Gaussian Processes.

  • Week 3

    Probabilistic aspects of shape models

    • Shape models and the normal distribution

      We discuss how the Gaussian Process assumption leads to flexible and practical computer implementations of shape models.

    • Probabilistic aspects of shape models in Scalismo

      Learn how to work with shape models as probability distributions in Scalismo.

    • Parametric representations of shape models

      There are many ways to represent shape variations. We introduce a classical one and discuss why it is so useful for shape modelling.

  • Week 4

    Modelling with Gaussian Processes

    • Modelling with kernels

      Gaussian Processes are great for modelling. Here we discuss how we can model shapes even if we don't have example data available.

    • Modelling with kernels in Scalismo

      Let's play. Model shape variations using kernels in Scalismo.

    • Flexibility of statistical shape models

      Learn how you can use Gaussian Processes to overcome the model-bias in cases where there is insufficient example data.

    • Half-time!

      Time to celebrate your progress and look ahead.

  • Week 5

    Reconstructing missing parts

    • Shape modelling in medical practice

      See how shape modelling is employed in diagnosis, surgery planning and for designing splints and implants.

    • Incorporating known deformations into shape models

      Sometimes we know a part of a shape and want to model the variation of the unseen part. Learn how Gaussian Process regression can be used to solve this problem in a mathematically elegant way.

    • Gaussian Process regression in Scalismo

      Practice Gaussian Process regression in Scalismo and use it to retrieve Professor Vetter's missing nose.

    • Femur project

      Prepare the data for building your own femur model.

  • Week 6

    Fitting models to data

    • The fitting problem

      Learn how you can use shape models to compare and analyse surfaces.

    • Iterative Closest Points in Scalismo

      Apply Iterative Closest Point (ICP) in Scalismo to rigidly align shapes and fit a shape model to a surface mesh.

    • Femur project

      Your assignment: build a statistical femur model and use it to complete partial shapes.

  • Week 7

    Model-based image analysis

    • Fitting shape models to images

      Shapes are most often found implicitly in images. We discuss how we can extend our fitting method to images.

    • Fitting images in Scalismo

      Learn how to build intensity models in Scalismo and use them to find corresponding points in an image.

    • Femur project: progress

      How are you doing with the project? Ask your questions here.

  • Week 8

    Conclusion and outlook

    • Applications and future directions

      Get an impression of how shape models are used today and discuss with us how we can shape the future.

    • Femur project

      How did it go? How did your reconstruction perform on the leader board?

    • Summary and outlook

      Find out how you can continue your learning journey.

When would you like to start?

  • Date to be announced

Add to Wishlist to be emailed when new dates are announced

Learning on this course

You can take this self-guided course and learn at your own pace. On every step of the course you can meet other learners, share your ideas and join in with active discussions in the comments.

What will you achieve?

By the end of the course, you‘ll be able to...

  • Model the normal shape variations of anatomical shapes using Gaussian processes
  • Explore the mathematical concept of Gaussian processes visually on 3D shapes
  • Apply the theoretical concepts of shape modelling to clinically relevant problems in shape and image analysis
  • Develop programs for building and fitting statistical shape models to images using the open source software Scalismo

Who is the course for?

This course is intended for students and professionals with a Bachelor in computer science, medical imaging professionals and biological anthropologists, who are interested in top-notch research, scientific insights and a useful application. Please note that tutoring takes place between March 1, 2021 and May 2 2021

Although you can watch the videos, read the articles, and complete the tests and quizzes on mobile devices such as smartphones or tablets, you will have to install the free software Scalismo on your own workstation in order to use it – there is no online version available.

In order to be able to do this, your computer should meet the following minimum system requirements: Windows (32bit/64bit), Mac OS X or Linux (64bit), 4GB of RAM, 500MB of free HD space. There are no special requirements for the graphic adapter.

What software or tools do you need?

To take part in this course, you need to download and install Scalismo Lab and create your account on SMIR.

What do people say about this course?

"Very excellent course. Great mix of theory and practical application."

Who will you learn with?

I am researcher in computer science at the University of Basel. My research focus is the mathematical modelling of shapes and its application to medical image analysis.

I am a scientific collaborator at the mathematics and computer science department of the University of Basel and one of the developers of Scalismo: https://github.com/unibas-gravis/scalismo

Who developed the course?

University of Basel

The University of Basel has an international reputation of outstanding achievements in research and teaching.

Learning on FutureLearn

Your learning, your rules

  • Courses are split into weeks, activities, and steps, but you can complete them as quickly or slowly as you like
  • Learn through a mix of bite-sized videos, long- and short-form articles, audio, and practical activities
  • Stay motivated by using the Progress page to keep track of your step completion and assessment scores

Join a global classroom

  • Experience the power of social learning, and get inspired by an international network of learners
  • Share ideas with your peers and course educators on every step of the course
  • Join the conversation by reading, @ing, liking, bookmarking, and replying to comments from others

Map your progress

  • As you work through the course, use notifications and the Progress page to guide your learning
  • Whenever you’re ready, mark each step as complete, you’re in control
  • Complete 90% of course steps and all of the assessments to earn your certificate

Want to know more about learning on FutureLearn? Using FutureLearn

Do you know someone who'd love this course? Tell them about it...

You can use the hashtag #FLstatisticalshapes to talk about this course on social media.