MSc Health Data Science / Course details

Topics covered will include (but are not limited to):

• Basic image processing
  • Noise models, image filtering, resampling, region analysis
• Methods for object detection and evaluation methods
• Image segmentation methods and evaluation metrics
• Image registration (linear and deformable approaches)
• Deep learning for vision and representation learning
  • Deep learning fundamentals
  • Convolutional neural networks (CNN)
  • Medical imaging applications in segmentation and registration

Introductory materials will be made available using e-learning and via Blackboard.

• Introduce key image processing tools and methodologies for medical image analysis.
• Introduce machine learning techniques for medical image interpretation and processing.
• Introduce evaluation metrics for the assessment of medical image analysis methods
• Introduce key Python libraries for image analysis
   

The course will be delivered as either in person 12 x 90 minute lectures, each typically supplemented with 15-30 minutes of discussion and and followed by a 60-minute practical session.

Lectures will be reinforced by practical exercises backed up with online reading material in the form of research papers and purpose-written tutorials.

Exercises will be given at the end of each lecture in order to introduce intellectual content via task-based learning. Solutions will be discussed prior to delivery of each week’s new material to receive regular feedback. 

Towards the end of the semester, the understanding of AI-based image processing techniques will be consolidated in two written assignments (the first formative followed by another summative) investigating the impact of modifications such as network architecture, optimizer selection, data pre-processing and parameter tuning on the model performance and efficiency using evaluation metrics.

1. Understanding of digital image processing techniques to lay a solid foundation for medical image analysis. 
2. Understanding of deep learning principles and their application in medical image computing for tasks such as image registration and segmentation.
3. Knowledge in evaluating medical image analysis methods, employing suitable validation metrics, and interpreting results in scientific reports.

1. Select and apply appropriate techniques for medical image processing, including intensity processing; frequency processing, spatial and spectral filtering; morphological processing.

1. Use Python code for practical image processing tasks and the implementation of deep learning models. 
2. Critically assess the output based upon knowledge of intended outcome and evaluation methodology.

1. Undertake a project in medical image analysis 
2. Write a scientific report

Formal summative assessments

The material for this course comes from a variety of sources and is not available in a single reference text. However, some parts of the material are covered in the following:

• Medical Image Analysis ed. Frangi et al. 2024.
• Guide to Medical Image Analysis_ Methods and Algorithms_ Advances in Computer Vision and Pattern Recognition [Toennies 2012-02-06]
• Handbook of Medical Imaging, Processing and Analysis, Isaac N. Bankman (Editor in chief), Academic Press, 2000.

Further reading:

• J. Kaur and W. Singh, “Tools, techniques, datasets and application areas for object detection in an image: a review,” Multimedia Tools and Applications, 2022. DOI: 10.1007/s11042-022-13153-y
• F. P. M. Oliveira and J. M. R. S. Tavares, “Medical image registration: A review,” Computer Methods In Biomechanics & Bio Engineering, 2014, 17(2):73-93. DOI: 10.1080/10255842.2012.670855
• A S Lundervold and A. Lundervold “An overview of deep learning in medical imaging focusing on MRI,” Zeitschrift für Medizinische Physik, 2018. https://doi.org/10.1016/j.zemedi.2018.11.002