Duration
10h Th, 10h Mon. WS
Number of credits
| Master in bio-informatics and modelling, research focus | 2 crédits |
Lecturer
Coordinator
Language(s) of instruction
English language
Organisation and examination
Teaching in the second semester
Schedule
Units courses prerequisite and corequisite
Prerequisite or corequisite units are presented within each program
Learning unit contents
This course introduces advanced biological and biomedical image analysis with the support of artificial intelligence-based techniques
The main objective is to understand how an image can be transformed into usable quantitative data.
Indicative programme
- Review and deepen the fundamental concepts of image analysis and mathematical morphology: pixels, file formats, bit-depth, noise, blur, LUTs, clipping, stacks/hyperstacks, filters, background subtraction, thresholding, watershed, measurements and colocalization.
- Introduce artificial intelligence applied to biological image analysis: machine learning, deep learning, CNNs, U-Net, semantic segmentation and instance segmentation, pre-trained models, model retraining or adaptation, advantages and limitations.
- Move from cellular objects to multiparametric data: feature selection, normalization, clustering, dimensionality reduction and visualization of cell populations.
Learning outcomes of the learning unit
This course aims to provide students with the conceptual foundations needed to understand how multidimensional biological images, produced in various experimental contexts, can be transformed into usable quantitative data. At the end of the course, students should be able to identify the main steps of an image analysis workflow, explain the role of annotations, segmentation, measurement extraction, classification and spatial analysis, and understand the contribution of artificial intelligence tools. They should also be able to critically discuss the quality of the results obtained, possible biases, methodological or biological limitations, and the conditions required for reproducible image analysis.
Prerequisite knowledge and skills
This course does not require any specific prior knowledge in computer science, but it nevertheless builds on the introduction to image analysis provided in the BIOC0727-1 course.
Planned learning activities and teaching methods
Learning activities combine short lectures, demonstrations and guided computer practicals and case studies.
Mode of delivery (face to face, distance learning, hybrid learning)
Face-to-face course
Course materials and recommended or required readings
Platform(s) used for course materials:
- eCampus
Exam(s) in session
Any session
- In-person
oral exam
Work placement(s)
Organisational remarks and main changes to the course
Each student should bring a laptop on which QuPath and Fiji/ImageJ can be installed and run.
Contacts
- Pierre Tocquin: ptocquin@uliege.be
- Alexandre Hego: alexandre.hego@uliege.be