XClose

UCL Module Catalogue

Home
Menu

Computational Modelling for Biomedical Imaging (COMP0118)

Key information

Faculty
Faculty of Engineering Sciences
Teaching department
Computer Science
Credit value
15
Restrictions
Restriction: This module is restricted to students registered on: MSc Computer Graphics, Vision and Imaging MSc Computational Statistics and Machine Learning MSc Data Science and Machine Learning MSc Machine Learning MRes Robotics MSc Robotics and Computation MRes Medical Physics and Biomedical Engineering MSc Scientific Computing MEng Computer Science MEng Mathematical Computation

Alternative credit options

There are no alternative credit options available for this module.

Description

Aims:

To expose students to the challenges and potential of computational modelling in a key application area. To explain how to use models to learn about the world. To teach parameter estimation techniques through practical examples. To familiarize students with handling real data sets.

Learning outcomes:

On successful completion of the module, a student will be able to:

1.understand the aims of biomedical imaging;

2.understand the advantages and limitations of model-based approaches and data-driven approaches;

3.have knowledge of standard techniques in modelling, experimental design and parameter estimation;

4.understand the challenges of data modelling, experiment design and parameter estimation in practical situations;
5.handle real-world data in computer programs;

Content:

-The module introduces the basics of mathematical modelling: the distinction between models and the real world; when and how models are useful; advantages and disadvantages of explicit model-based approaches;
-The module covers a range of model based approaches to biomedical imaging and image analysis and basic computer science techniques that underpin them. The intention is to introduce the students to standard techniques of parameter estimation in a hands-on practical way within the context of model-based imaging and image-based modelling.

- The module also gives exposure to common applications and challenges in biomedical imaging. It uses several example applications (including microstructural MRI and disease progression modeling) to introduce different kinds of model and, more fundamentally, new algorithms and techniques for parameter estimation, optimization, sampling and validation;

Requisites:

In order to be eligible to select this module, a student must be registered on a programme for which it is a formally approved option or elective choice.

The module makes heavy use of Matlab programming for courseworks, although a strong programmer in other languages will pick up the necessary Matlab during the course. It also assumes a strong grasp of general engineering mathematical concepts, in particular linear algebra (intermediate), probability and statistics (intermediate), geometry, and calculus.

Students familiar with statistical modeling, parameter estimation, and machine learning will pick up the content fairly easily; those less familiar with such concepts sometimes find the workload heavy. To get an idea of the content, have a look at section IV (Probabilities and Inference) of the Mackay Information Theory, Inference and Learning Algorithms book: Mackay Information Theory, Inference and Learning Algorithms book.

Module deliveries for 2020/21 academic year

Intended teaching term: Term 2     Postgraduate (FHEQ Level 7)

Teaching and assessment

Mode of study
Face-to-face
Methods of assessment
45% Project report
35% Coursework 1
15% Coursework 2
5% Project presentation
Mark scheme
Numeric Marks

Other information

Number of students on module in previous year
17
Module leader
Professor Daniel Alexander
Who to contact for more information
cs.compgrcvr@ucl.ac.uk

Intended teaching term: Term 2     Undergraduate (FHEQ Level 7)

Teaching and assessment

Mode of study
Face-to-face
Methods of assessment
35% Coursework 1
15% Coursework 2
45% Project report
5% Project presentation
Mark scheme
Numeric Marks

Other information

Number of students on module in previous year
5
Module leader
Professor Daniel Alexander
Who to contact for more information
cs.compgrcvr@ucl.ac.uk

Last updated

This module description was last updated on 5th March 2020.