Basic knowledge of mathematics, programming, and digital signal/image processing. Familiarity with Python is recommended.
Students acquire the knowledge and develop the skills indicated below:
1. Understand the concepts of basic digital image formation, acquisition and processing in the spatial and frequency domains.
2. Understand the different modalities of medical imaging.
3. Understand the processes of extracting features from an image to perform segmentation, detection and classification processes.
4. Understand and know how to apply the fundamental tools to process medical images.
1. Introduction to medical image processing
2. Image enhancement and restoration
3. Image segmentation (2D and 3D)
4. Image registration (2D and 3D)
5. Introduction to machine learning
6. Introduction to deep learning
The subject is taught following a theoretical-practical methodology. Practical exercises will be proposed during the development of the topics, which will allow the concepts presented in these topics to be put into practice.
In addition, group practices will be carried out in which image processing challenges will be posed and solved following a hackathon approach .
Theory: midterm and final exam.
Practice: lab sessions and an interview.
Theory and practice must be passed independently (?5)
Theory: 70% final exam, 30% midterm
Practice: 50% lab work, 50% interview
Gonzalez & Woods ? Digital Image Processing
Dougherty ? Digital Image Processing for Medical Applications
Bankman ? Handbook of Medical Image Processing and Analysis
Optional online resources and image-processing repositories.