Bioimage informatics

BIO-410 / 4 crédits

Enseignant(s): Sage Daniel, Seitz Arne

Langue: Anglais

Summary

The course provides a comprehensive overview of methods, algorithms, and computational tools used in bioimage analysis. It introduces fundamental concepts and practical approaches to extract quantitative information from multidimensional images combining engineering methods with deep learning.

Content

To investigate biological processes, bioimage informatics emerged at the interface between microscopy, signal processing, computer science, and data science. Modern microscopes produce large volumes of high-resolution multidimensional data.  Efficient algorithms and software tools are therefore needed to automatically extract quantitative information from these images and transform it into interpretable biological measurements.

The course presents the theoretical concepts and practical aspects of common image reconstruction, image processing, image analysis, and bioimage data-analysis. It analyses underlying algorithms and deploys software tools to build automatic analysis workflows using commonly used environments such as Fiji/ImageJ, Napari, and Jupyter notebooks. The course is tailored to students interested in solving biological questions with imaging sciences. No prior experience in imaging is required.

 

Topics covered include:

- Imaging foundations: microscopy modalities, digital images, multidimensional data (3D, time, and multi channels) data manipulation, 5D visualization, image metrics

- Image processing: 3D image-processing algorithms, , reconstruction, deconvolution, denoising, stitching

- Image analysis:  object detection, segmentation, pixel classification, particle tracking, super-resolution localization microscopy

- Machine learning: classical machine learning and deep learning for image analysis

- Bioimage data analysis: workflow design, data clustering, spatial data analysis, multiplex image classification

 

The course combines lectures, and practical sessions., The knowledge acquired is applied to a mini-project during the second half of the semester.

 

A personal laptop is recommended to run open-source image-analysis software and to develop short scripts.

Keywords

Bioimage, microscopy, multidimensional images, image processing, image analysis, visualization, super-resolution, machine learning, deep learning, bioimage data analysis

 

 

Learning Prerequisites

Required courses

Basic knowledge in programming in any language

 

Learning Outcomes

  • Contextualise the main concepts of bioimage informatics and explain how microscopy images can be transformed into quantitative biological data
  • Apply and visualize multidimensional bioimage data, including 3D, time-lapse, and multiplex images
  • Manipulate methods for quantitative measurements from images and organize them into structured bioimage data
  • Construct image-analysis workflows, quantitative results, and uncertainty clearly.
  • Develop reproducible image-analysis workflows using open-source tools such as Fiji/ImageJ and Napari
  • Report image-analysis workflows, quantitative results, and uncertainty clearly

Transversal skills

  • Manage priorities.
  • Continue to work through difficulties or initial failure to find optimal solutions.
  • Use a work methodology appropriate to the task.
  • Demonstrate the capacity for critical thinking
  • Use both general and domain specific IT resources and tools
  • Communicate effectively with professionals from other disciplines.

Assessment methods

20% Homework, individual

  • In the first half of the semester: 4 homeworks on computer (2 weeks)

40% Mini-project by groups of 2-3 students

  • In the second half of the semester: Development of an image analysis tool for a real application in biology

40% End-term exam, individual

  • written exam with handwritten notes

Resources

Virtual desktop infrastructure (VDI)

No

Moodle Link

Dans les plans d'études

  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bioimage informatics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bioimage informatics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bioimage informatics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bioimage informatics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bioimage informatics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bioimage informatics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel
  • Semestre: Printemps
  • Forme de l'examen: Ecrit (session d'été)
  • Matière examinée: Bioimage informatics
  • Cours: 2 Heure(s) hebdo x 14 semaines
  • Projet: 2 Heure(s) hebdo x 14 semaines
  • Type: optionnel

Semaine de référence

Cours connexes

Résultats de graphsearch.epfl.ch.