Summer School XAI 2024
Dates: September 2-6, 2024
Place: Faculty of Informatics & Institute of Computer Science, Masaryk University, Brno, Czech Republic
From September 2 to 6, 2024, the Faculty of Informatics and the Institute of Computer Science at Masaryk University in Brno will host a summer school focused on Explainable Artificial Intelligence (XAI) in digital pathology. This educational program promises participants a comprehensive view of how artificial intelligence can be used in medical applications.
Experts from Google and Charité
Throughout the week, participants will engage in a series of lectures and practical exercises led by renowned experts, including Dave Steiner (Google), Norman Zerbe (Charité), Heimo Müller (Medical University Graz), Tomáš Brázdil (Masaryk University), Rudolf Nenutil (Masaryk Memorial Cancer Institute), and Petr Holub (Masaryk University/BBMRI-ERIC). Topics will range from the basics of pathology for computer scientists to advanced discussions on AI research, data management, and AI implementation in digital pathology.
Practical Training with Visualization Tools
The main focus of the summer school is on practical training, during which participants will work on projects using visualization tools like RatioPath pipeline and RatioViz. In addition to practical skills, the summer school will also cover the handling of sensitive data and the management of medical data.
What Will Graduates of the Summer School Gain?
Graduates will acquire not only practical experience in working with real data and creating AI models but also a deep understanding of the latest technologies and methods in the field of explainable artificial intelligence. The summer school represents a unique opportunity for those who want to be at the forefront of technological and medical breakthroughs and push the boundaries of AI utilization in medicine.
Registration information:
Registration for the Summer School closes on August 25th. Confirmation of the registration, along with additional information, will be sent to all registered participants by August 28th. The Summer School, including refreshments, is free of charge. Participants are only responsible for covering their travel and accommodation expenses.
Summer School Topics
- Introduction into XAI - what is explainability, why is it relevant for medical applications of AI [Tomáš Brázdil]
- Introduction into digital pathology - primary application use case of the summer school
- Pathology 101 for computer science students [Rudolf Nenutil]
- State-of-the-art of research in AI in digital pathology [David Steiner/Google]
- Data and their management in digital pathology
- Data in digital pathology [Norman Zerbe/Charité]
- Annotations, management of data across research and health care - example of DICOM
- Practical examples how data is accessed for AI models [Petr Holub/Vít Musil]
- How data and outcomes of models is visualized [Jiří Horák]
Imaging data - Quality control mechanisms [Markus Plaß]
- Data in digital pathology [Norman Zerbe/Charité]
- Handling sensitive data - principles requirements best practices [Petr Holub]
- Getting your hands dirty: practical training of diagnostic models and analyzing their explainability
Tentative Program
Monday [David Steiner as a guest]
10:00 - 10:15: Introduction by Petr Holub
10:15 - 12:15: "Introduction to Pathology" presented by Rudolf Nenutil
12:15 - 13:15: Lunch Break
13:15 - 15:15: "Intro to XAI on (not only digital pathology) Imaging" with Kay Aray
15:15 - 15:30: Break
15:30 - 18:00: "State of the Art in (X)AI in Digital Pathology" by David Steiner
19:00 - 22:00: Dinner
Tuesday [Norman Zerbe as a guest]
9:00 - 11:00: "Data in Digital Pathology - Images, Annotations, Metadata, Clinical Data. Clinical AI Applications" by Norman Zerbe
11:00 - 12:00: "Handling Sensitive Data" with Petr Holub
12:00 - 13:00: Lunch Break
13:00 - 14:00: "Onboarding into Cloud and SensitiveCloud" led by Petr Holub, Michal Růžička & Infra Team
14:00 - 16:00: "Introduction to RationAI Pipelines" presented by Vít Musil
16:00 - 16:30: Break
16:30 - 18:00: "Hands-on Working with Image Data in RationAI Pipelines - Getting Data Loaded" with Vít Musil
Wednesday
9:00 - 10:00: "Handling Data Quality" by Karel Štěpka
10:00 - 12:00: "Training Your First Simple AI Model in Digital Pathology"
12:00 - 13:00: Lunch Break
13:00 - 14:30: "XAI in Digital Pathology" presented by Kay Aray
14:30 - 18:00: "Project Hands-On" session
Thursday
9:00 - 9:30: "Full Day Project Assignment"
9:30 - 12:30: Project Work
12:30 - 13:30: Lunch Break
13:30 - 14:30: "Clinical Data Relevant for Pathology" by Rudolf Nenutil
14:30 - 16:30: "Mining Clinical Data" presented by Aleš Horák
16:30 - 18:00: Project Work - Consulting Results
Friday
9:30 - 12:30: Project Work - Consulting
12:30 - 13:30: Lunch Break
13:30 - 14:30: Wrap Up of the School by Petr Holub