Course content

This course will introduce basic notions and concepts related to medical data manipulation with a special focus on medical imaging technologies and the new deep learning-based approaches for capturing, representing, processing and analysing such data. It will also present selected applications of such processing and analysis in the healthcare domain.

The topics covered in this course include but are not limited to the following:

• Medical data in healthcare: history and motivation.
• Medical image acquisition modalities: US, RX, MRI, CT, PET, etc.
• Medical data file formats, visualization and rendering.
• Medical image quality assessment.
• Medical images pre-processing (quantization, enhancement, denoising, artefact removal, etc.).
• Segmentation.
• Abnormality detection and classification.
• Quantitative medical image analysis for diagnosis and therapy.
• Selected Applications (Screening, image-guided navigation, treatment and interventions).

Learning outcome

Knowledge:

Having completed the course, the students will:

• Possess advanced knowledge and insight in the main imaging modalities (RX, CT, MRI, PET, US, etc.), the reconstruction methods, and the physical parameters that influence image quality such as spatial resolution, noise, artefacts and contrast.
• Possess specialized insight and good understanding of the research frontier in selected topics of medical image processing and analysis.
• Possess advanced understanding of the most recent trends in medical image processing and visualization, and its use in various clinical applications including diagnosis, and therapy.

Skills:

The student should be:

• able to explain the principles of medical imaging and image analysis.
• able to identify strengths, weaknesses and opportunities in the context of medical imaging technology.
• able to critically review literature and case studies in this field.
• able to use insights to solve new problems in the area.
• able to express an opinion, review, and counter argue someone else's opinion in a written essay.

General competence:

The student should be:

• able to present and discuss the results of research work, to computer scientists and subject matter experts, and to general public.
• abile to communicate (in a written form and orally) academic issues, analyses, and conclusions.
• have the learning skills to continue acquiring new knowledge and skills in a manner that is largely self-directed.
• capable of using relevant and suitable methods when carrying out further research and development activities in the area of medical image capture, analysis and processing.
• able to perform a critical review of relevant literature when solving assigned problem or topic.
• able to reflect on the implications of the use of medical data and AI on the sustainability of healthcare services.

Learning methods and activities

• E-learning and Seminars:

Additional information: Lectures by the course instructors and guest lectures by invited experts. Student presentations on selected topics.

E-learning material will be available for this course: PDF of the lectures and student presentations, and possibly audio/video recordings of the lectures will be provided. These E-lectures material will be available on an e-Learning platform (Blackboard). Which will also be used for discussions between teachers and students.

Compulsory requirements: - Oral presentations: Each student needs to study a selected topic, make a short introductory presentation (5min) about it and later give a deeper presentation (20-30min) and write a report about the work done and its outcomes (code, dataset, paper draft).

Compulsory assignments

• Mandatory project report and presentation.

Further on evaluation

Re-sit: One re-sit for the Oral re-examination may be offered for valid reasons only, needs to have passed the required: presentation and report.

Forms of assessment: - 20-30 min Oral Exam, individually (counts 100%, evaluated by lecturers and external reviewer) / video conference via videoconferencing for distance students may be arranged - Topic report (is a pre-requisite to take the exam and is evaluated by lecturers as pass/fail). - Each part must be individually approved.

Specific conditions

Recommended previous knowledge

Good knowledge in machine learning, image and video processing or analysis.

Required previous knowledge

Basic knowledge of machine learning, image/video processing and analysis or equivalent courses (e.g., IMT4135 Introduction to Research on Colour and Visual Computing).

Admission to a programme of study is required:Applied Computer Science (MACS)

Course materials

Recent research papers and book chapters from various books. Material will be published on the course pages before the start of the course.