Krakow Conference on Computational Medicine 2025

Date and time: 15 October 2025 at 15:30 pm 

Place:

Sano Centre for Computational Medicine
room 109 in CE building, entrance C5
Czarnowiejska 36,  Kraków

Maximum number of participants: 20

Duration: 4h

Wioletta Niwińska¹, Anna Kajda-Twardowska¹, Michał Kosobudzki¹

¹Sano – Centre for Computational Medicine, Czarnowiejska 36, 30-054 Kraków, Poland

w.niwinska@sanoscience.org a.kajda@sanoscience.org, m.kosobudzki@sanoscience.org  

Keywords: AI law, compliance, data protection, IP law   

1. Introduction 

The implementation of projects, particularly involving AI solutions, imposes the need to exercise due diligence to safeguard the interests of creators, companies, software owners, but also to ensure the safety of end users. Looking at AI projects from a broader perspective is key to securing and developing AI systems that comply with normative principles, rules and standards of trustworthiness.   

The implementation of AI tools requires multidisciplinary teams, which is possible for large entrepreneurs and difficult to achieve for smaller entities such as startups. Compliance with trustworthy AI and responsible AI principles and their proper consideration in the process of building AI solutions can determine the success of the entire project and is key to building public trust for AI technologies.   

2. Description of the tutorial 

The workshop is scheduled for half a day (4 hours).  The training will include a presented and moderated discussion and a practical part. The first will focus on providing the necessary theoretical knowledge on the subject of the workshop. It will be based on presenting the basic theoretical concepts, listing the main legal basis and conveying the practical aspects of implementing an AI-based project. The presentation will also include time for a moderated discussion with workshop participants to share their own experience or ask additional questions. The presenters during the first part of the workshop will share, in addition to theoretical knowledge, practical tips developed during their professional work.  

The second part of the workshop will be dedicated to practical tasks so that participants can stimulate their creative thinking in an interactive way, practice negotiation and consolidate the information acquired during the first part of the workshop.  
The aim of the workshop tasks will be to try to play the roles of the various participants in the process of developing and implementing AI projects and to prepare an AI project implementation plan with a view to safeguarding the legal interests of the parties, with a view to acting in accordance with the law. Participants will be divided into groups and randomly assigned roles that may occur in the process of developing AI solutions. During this part, the Walt Disney working methodology will also be used, which is a creative problem-solving technique that involves analysing issues from three different perspectives: the dreamer, the realist and the critic. Developed by Robert Dilts, this method aims to support the creative process and decision-making in a systematic and sustainable way which fits in with the general approach of responsible AI and trustworthy AI.  

During the workshop part, in addition to the instructions given, participants will have space to work creatively, make their own assumptions and share their own experiences and ideas. The training will conclude with a joint discussion on the exchange of experiences, including the preparation of a list of ‘golden bullets’ – what to keep in mind. The trainers will actively support the participants without, however, interfering with their ideas or solutions. In the workshop part, the trainers will act as moderators. 

We hope that at the end of the workshop participants will have gained new knowledge and will have created a practical summary in the form of golden bullets. This list will be a summary of what took place during the workshop and the participants’ individual reflections, allowing them to recall and consolidate the new skills and knowledge acquired during the workshop. 

The target group of the workshop is the conference participants, regardless of their legal background, who may have different roles in the implementation of the AI project. The participation of representatives from different groups will allow the identification of legal risks from their perspective but may also lead to the development of a common way to mitigate them. The workshop is addressed both to people from the legal world (law students, lawyers) and the broader business world, including developers, C-suite, board of directors, compliance and data protection specialists, engineers and AI architects and people who do not have any experience in implementing AI tools such or those who plan to retrain into the world of artificial intelligence specialization.  

3. Knowledge and skills to be gained 

The aim of this workshop is to respond to the needs of lawyers and those working with AI systems who may encounter difficulties related to the legal regulation of advanced solutions in their daily work. The workshop is intended to lead to an increased awareness among participants of the complexity of legal regulations that need to be considered when developing AI solutions. Through this workshop, participants will gain tips on the information needed to verify and the steps worth planning when creating AI solutions. During the workshop, speakers will share their experience in the legal security of the project being developed with a particular focus on IP and data protection issues. This workshop will be a space to share good practices. We hope that this workshop will inspire participants to plan projects outside the box and to look for unusual and creative solutions. IP and data issues are crucial elements of any AI software. It is hoped that the universality of the topic will enable the knowledge gained to be applied to most AI and Law projects and contribute to broad interest of the workshop by the audience. The workshop will provide an opportunity for participants to share their experiences and will be a platform for knowledge exchange, as well as an opportunity for networking. The value for the participants will be to broaden their horizons in terms of their roles and assigned responsibilities, which will allow them to more easily understand the perspective of the other people and entities acting within the project.  

References 

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3822924 

https://ec.europa.eu/futurium/en/ai-alliance-consultation/guidelines/1.html 

https://airc.nist.gov/airmf-resources/airmf/3-sec-characteristics/ 

Drexl, Hilty et al., Technical Aspects of Artificial Intelligence: An Understanding from an Intellectual Property Law Perspective,Version 1.0, October 2019, available at: https://ssrn.com/abstract=3465577  

https://tipsforyourwebsite.com/what-are-project-management-methodologies/ https://mgrush.com/blog/agile-vs-waterfall/ 

https://www.forbes.com/councils/forbestechcouncil/2022/04/20/managing-the-data-for-the-ai-lifecycle/ 

https://intellectual-property-helpdesk.ec.europa.eu/news-events/news/artificial-intelligence-and-copyright-use-generative-ai-tools-develop-new-content-2024-07-16-0_en 

Max Planck Institute for Innovation and Competition. (2021). Artificial Intelligence and Intellectual Property Law – Position Statement of the Max Planck Institute for Innovation and Competition of 9 April 2021 on the Current Debate (Research Paper No. 21-10). SSRN. https://doi.org/10.2139/ssrn.3822924

Date and time: 15 October 2025 at 15:30 pm  

Place:

Sano Centre for Computational Medicine
2nd floor in CE building, entrance C5
Czarnowiejska 36,  Kraków

Maximum number of participants: 12

Duration: 1h

Karol Zając¹, Piotr Nowakowski^1,2, and Levente Sandor³

¹Sano Centre for Computational Medicine, Czarnowiejska 36, 30-054 Kraków, Poland
²ACC Cyfronet AGH, ul. Nawojki 11, 30-950 Kraków, Poland
³Department of Hydrodynamic Systems, Budapest University of Technology and Economics, Faculty of Mechanical Engineering, Műegyetem rkp. 3, H-1111 Budapest, Hungary
{k.zajac,p.nowakowski}@sanoscience.org, lsandor@hds.bme.hu

Keywords: VVUQ, Sensitivity Analysis, Workflow Automation, Large-Scale, HPC

1. Introduction

This tutorial introduces participants to modern tools for Verification, Validation, and Uncertainty Quantification (VVUQ) in scientific modeling, with a focus on automating and scaling VVUQ workflows on High-Performance Computing (HPC) infrastructure. Through the use of the EasyVVUQ library and Dask parallel computing framework, researchers can efficiently run complex Sensitivity Analysis (SA) and Uncertainty Quantification (UQ) campaigns across many simulations. The session aims to demonstrate how these tools integrate seamlessly with HPC schedulers such as SLURM and MPI environments, enabling robust, reproducible, and scalable VVUQ pipelines.

2. Description of the tutorial

This 1-hour hands-on tutorial blends conceptual introduction with live demonstrations. It is designed for researchers and software engineers looking to adopt or streamline VVUQ methodologies in their computational workflows. The session will cover:

1. VVUQ Concepts and Motivation: Introduction to VVUQ in scientific computing.
2. Automating VVUQ with EasyVVUQ: Learn to define parameters, set up encoders/decoders, and run campaigns with EasyVVUQ.
3. Scalable Execution with Dask: Use Dask (JobQueue/MPI) with SLURM to distribute jobs and monitor performance.
4. Use Case: Hemodynamics Simulation Campaign (VirtualFD): Hands-on application to a real-world example from GEMINI project.

3. Knowledge and skills to be gained

By the end of this tutorial, participants will be able to:

• Understand the principles of VVUQ and their role in computational modeling.
• Set up and manage VVUQ workflows using EasyVVUQ.
• Configure and run large-scale UQ/SA simulations using EasyVVUQ and Dask.
• Analyze and visualize sensitivity and uncertainty results efficiently.
 

Acknowledgements: This tutorial is made possible by the contributions and results from the following projects: InSilicoWorld (grant agreement no. 101016503), GEMINI (grant agreement no. 101083771).

References:

 Dask Distributed documentation web site: https://distributed.dask.org/en/stable

InSilicoWorld project: https://insilico.world/

GEMINI project: https://dth-gemini.eu 

Suleimenova, D., Arabnejad, H., Edeling, W., Coster, D., Luk, O., Lakhlili, J., … Groen, D. (2021). Tutorial applications for Verification, Validation and Uncertainty Quantification using VECMA toolkit. Journal of Computational Science, 53. doi:10.1016/j.jocs.2021.101402

P.L.J. Hilhorst, B.B.E. van de Wouw, K. Zajac, M. van ’t Veer, P.A.L. Tonino, F.N. van de Vosse and W. Huberts. “Sensitivity analysis for exploring the variability and parameter landscape in virtual patient cohorts of multi-vessel coronary artery disease.” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 383, no. 2293. https://doi.org/10.1098/rsta.2024.0230

EasyVVUQ: Uncertainty intervals for everyone: https://easyvvuq.readthedocs.io/en/dev/

Date and time: 15 October 2025 at 15:30 pm  

Place:

Sano Centre for Computational Medicine
3rd floor in CE building, entrance C5
Czarnowiejska 36,  Kraków

Maximum number of participants: 10

Duration: 3h

Jan K. Argasiński¹, Cemal Koba¹, Rosmary Blanco¹, Monika Pytlarz¹

¹Sano – Centre for Computational Medicine, Czarnowiejska 36, 30-054 Kraków, Poland
j.argasinski, c.koba, r.blanco, m.pytlarz@sanoscience.org

Keywords: Computational neuroscience, brain-gut axis, methodology, study design

1. Introduction

The brain–gut axis, a bidirectional communication network linking the central nervous system and the gastrointestinal tract, is emerging as a interesting domain in understanding neurological, metabolic, and psychiatric disorders. Despite growing biological and clinical interest, computational approaches to studying the brain–gut axis remain basic. This tutorial responds to the need for a methodological framework for researchers aiming to explore the brain–gut axis from a computational neuroscience perspective. Focusing on scientific literature as both a source of knowledge and a foundation for study design, the session will introduce participants to modern tools and strategies for initiating research in this field.

2. Description of the tutorial

This 3-hour tutorial serves as both a literature deep-dive and a methodology primer. Participants will work in a guided exploration of the latest scientific publications on the brain–gut axis, with a particular focus on computationally relevant research.

The session is divided into three components:

Literature Exploration and Mapping:
Participants will learn systematic methods for identifying, filtering, and categorizing relevant literature using tools like PubMed, Scopus, and AI-powered search engines (e.g., Semantic Scholar, Connected Papers). Emphasis will be placed on extracting methodological content, modeling approaches, and data sources.

Scientific Methodology for Study Planning:
We will demonstrate how to analyze existing studies to extract assumptions, computational models, and data modalities (EEG, fMRI, microbiome profiles, behavioral markers). Participants will collaboratively map gaps and research opportunities, developing hypotheses based on the current state of the field.

Pipeline Prototyping for Brain–Gut Studies:
The final part of the session will be a walkthrough of how to draft a computational research pipeline. This includes defining input data, identifying possible modeling techniques (e.g., neural networks, graph-based models, Bayesian inference), and conceptualizing evaluation strategies.

The goal is to help participants move from reading to research planning.
The format includes short lectures, guided group work, and discussion.

3. Knowledge and skills to be gained

By the end of the tutorial, participants will be informed on how to:

• Conduct literature reviews focused on computational neuroscience topics.
• Identify and extract methodological insights from scientific publications.
• Recognize and categorize computational approaches applicable to brain–gut research.
• Formulate basic study designs for modeling the brain–gut axis.
• Draft conceptual pipelines for computational experiments, including data selection, modeling strategies, and analysis plans.
• Understand the interdisciplinary landscape of brain–gut research and the role of computational tools within it.

Acknowledgements: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 857533 and from the International Research Agendas Programme of the Foundation for Polish Science No MAB PLUS/2019/13. The tutorial was created within the project of the Minister of Science and Higher Education “Support for the activity of Centers of Excellence established in Poland under Horizon 2020” on the basis of the contract number MEiN/2023/DIR/3796. We gratefully acknowledge Poland’s high-performance Infrastructure PLGrid ACC Cyfronet AGH for providing computer facilities and support within computational grant no. PLG/2025/018289.
 

References:

Burns, J. L. (2009). The Scientific Method through the Lens of Neuroscience; From Willis to Broad. In Forum on Public Policy Online (Vol. 2009, No. 2). Oxford Round Table. 406 West Florida Avenue, Urbana, IL 61801.

Mayer, E. A., Nance, K., & Chen, S. (2022). The gut–brain axis. Annual review of medicine, 73(1) 439-453.

Mayer, E. A., Naliboff, B. D., & Craig, A. B. (2006). Neuroimaging of the brain-gut axis: from basic understanding to treatment of functional GI disorders. Gastroenterology, 131(6), 1925-1942.

Date and time: 15 October 2025 at 15:30 pm 

Place:

Sano Centre for Computational Medicine
room 112 in CE building, entrance C5
Czarnowiejska 36,  Kraków

Maximum number of participants: 10

Duration: Nh

Przemysław Korzeniowki¹,Kuba Chrobociński^1,2, and Michał Motak¹

¹Sano Centre for Computational Medicine, Czarnowiejska 36, 30-054 Kraków, Poland
²Division of Clinical Medicine, School of Medicine & Population Health, University of Sheffield, S1 2TN, Sheffield, United Kingdom

p.korzeniowski@sanoscience.org, k.chrobocinski@sanoscience.org, m.motak@sanoscience.org

Keywords: Virtual Reality, Medical Imaging, Visualisation, Data Interaction

1. Introduction

While Virtual and Augmented Reality (VR/AR) are widely recognised for their entertainment applications, their utility is rapidly expanding across diverse industries. Beyond popular uses in gaming, flight, and driving simulators, these technologies offer safe and cost-effective platforms for skill development and gaining practical insights. Immersive simulations, in particular, mitigate the risks and expenses associated with traditional training methods.

The medical field stands out as a particularly promising area for VR. Its applications range from psychology and surgery to comprehensive training programs. These demonstrate not only cost-effectiveness but also the ability to introduce novel elements that significantly enhance user perception and engagement.

2. Description of the tutorial

The tutorial will introduce basic concepts used for the development of interactive environments in Unity Game Engine for medical applications. DICOM images import and interaction are going to be presented. Example Virtual Reality environments will be explored, and their strong sides and limitations are going to be discussed. Surgical training simulators leveraging haptic devices will be presented.

3. Knowledge and skills to be gained

Basic Unity Game Engine concepts
Challenges associated with Virtual Reality for medical imaging
Setting up a simple visualisation of a 3D image in VR using Unity Game Engine
Usage of Surgical Simulators with Haptic Feedback

Acknowledgements: This work is supported by the European Union’s Horizon 2020 research and innovation program under grant agreement no. 857533 (Sano) and the International Research Agendas program of the Foundation for Polish Science, co-financed by the European Union under the European Regional Development Fund.

References:

J. Qian, D. J. McDonough, and Z. Gao. The effectiveness of virtual reality exercise on individual’s physiological, psychological and rehabilitative outcomes: a systematic review. International journal of environmental research and public health, 17(11):4133, 2020

P. Korzeniowski, S. Płotka, R. Brawura-Biskupski-Samaha and A. Sitek, “Virtual Reality Simulator for Fetoscopic Spina Bifida Repair Surgery,” 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, 2022, pp. 401-406, doi: 10.1109/IROS47612.2022.9981920. keywords: {Training;Pregnancy;Solid modeling;Spinal cord;Computational modeling;Spine;Surgery},

A. D. Kaplan, J. Cruit, M. Endsley, S. M. Beers, B. D. Sawyer, and P. A. Hancock. The effects of virtual reality, augmented reality, and mixed reality as training enhancement methods: A meta-analysis. Human factors, 63(4):706–726, 2021

Date and time: 15 October 2025 at 15:30 pm 

Place:

Sano Centre for Computational Medicine
2nd floor, CE building, entrance C5
Czarnowiejska 36,  Kraków

Maximum number of participants: 10

Duration: Nh

Jose Sousa¹

¹Sano Centre for Computational Medicine, Czarnowiejska 36, 30-054 Kraków, Poland

j.sousa@sanoscience.org

Keywords: Explainable AI, Data Abstraction, Knowledge Graphs, Classification, Small Datasets 

1. Introduction

This Deep learning has achieved remarkable performance but often requires large datasets, significant computer resources, and lacks transparency, making it hard to trust in sensitive fields such as healthcare and law. The Comprehensive Abstraction and Classification [1–4] Tool for Uncovering Structures (CACTUS) offers a transparent and efficient approach by:

• Supporting small and incomplete datasets,
• Preserving the semantic meaning of categorical variables,
• Building interpretable knowledge graphs for feature interactions,
• Providing feature ranking and community analysis for explainable classification,
• Offering memory-efficient, parallelised analysis.

2. Description of the tutorial

This hands-on session introduces CACTUS for explainable AI and secure analytics. Participants will:

• Learn CACTUS architecture (decision tree, abstraction, correlation modules),
• Prepare datasets and YAML configs for flexible analysis,
• Abstract continuous and categorical features into interpretable forms,
• Generate and interpret knowledge graphs and feature rankings,
• Compare CACTUS with standard ML models on datasets like breast cancer, thyroid, heart disease, and its use on the allergies project.

3. Knowledge and skills to be gained

By the end of this tutorial, participants will be able to:

• Understanding Explainable AI and CACTUS methodology,
• Running CACTUS for binary and multi-class tasks,
• Visualising feature interactions with knowledge graphs,
• Interpreting feature rankings alongside decision trees and correlations, 
• Applying best practices for incomplete or small datasets.

Acknowledgements: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 857533 and from the International Research Agendas Programme of the Foundation for Polish Science No MAB PLUS/2019/13. The tutorial was created within the project of the Minister of Science and Higher Education “Support for the activity of Centres of Excellence established in Poland under Horizon 2020” on the basis based on contract number MEiN/2023/DIR/3796. We gratefully acknowledge Poland’s high-performance Infrastructure, PLGrid ACC Cyfronet AGH , for providing computer facilities and support within the computational grant no. PLG/2025/018289.

References:

Paulina Tworek, Maja Szczypka, Julia Kahan, Marek Mikołajczyk, Roman Lewandowski, and Jose Sousa. 2025. Artificial Intelligence in Medicine, 23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part I. (2025), 448–456. https://doi.org/10.1007/978-3-031-95838-0_44

Anna Drożdż, Brian Duggan, Mark W. Ruddock, Cherith N. Reid, Mary Jo Kurth, Joanne Watt, Allister Irvine, John Lamont, Peter Fitzgerald, Declan O’Rourke, David Curry, Mark Evans, Ruth Boyd, and Jose Sousa. 2024. Stratifying risk of disease in haematuria patients using machine learning techniques to improve diagnostics. Front. Oncol. 14, (2024), 1401071. https://doi.org/10.3389/fonc.2024.1401071

Luca Gherardini, Paulina Tworek, Maja Szczypka, Yousef Khan, Marek Mikołajczyk, Roman Lewandowski, and Jose Sousa. 2025. Artificial Intelligence in Medicine, 23rd International Conference, AIME 2025, Pavia, Italy, June 23–26, 2025, Proceedings, Part II. (2025), 171–175. https://doi.org/10.1007/978-3-031-95841-0_32

Luca Gherardini, Varun Ravi Varma, Karol Capała, Roger Woods, and Jose Sousa. 2024. CACTUS: a Comprehensive Abstraction and Classification Tool for Uncovering Structures. ACM Trans. Intell. Syst. Technol. 15, 3 (2024), 1–23. https://doi.org/10.1145/3649459

Date and time: 15 October 2025 at 15:30 pm 

Place:

Academic Computer Centre CYFRONET
of the AGH University of Krakow
Nawojki 11 street
30-950 Kraków

Maximum number of participants: 20

Duration: 2h

Marek Kasztelnik², Piotr Nowakowski^1,2, and Piotr Połeć²

¹Sano Centre for Computational Medicine, Czarnowiejska 36, 30-054 Kraków, Poland
²ACC Cyfronet AGH, ul. Nawojki 11, 30-950 Kraków, Poland
{p.nowakowski}@sanoscience.org, {m.kasztelnik,p.polec}@cyfronet.pl

Keywords: modelling, simulation, HPC, SLURM, Model Execution Environment

1. Introduction

This tutorial provides an introduction to High-Performance Computing (HPC) and its application in scientific research. Participants will be guided through the fundamental concepts of HPC, learning how to leverage powerful computing resources for their research needs. The tutorial will feature the Model Execution Environment (MEE), a platform designed to simplify the execution of complex simulations and data analysis pipelines on HPC infrastructure. We will explore how MEE supports the integration and execution of scientific applications, drawing on real-world examples from European research projects.

2. Description of the tutorial

This 2-hour tutorial will be a blend of lectures and live demonstrations. The session will cover the following topics:

• Introduction to HPC and the SLURM queuing system: We will begin with an overview of HPC concepts and a practical guide to using the SLURM workload manager for submitting and managing jobs on a cluster.
• API-driven job submission: This segment will focus on programmatic job submission. Participants will learn how to use an API to submit jobs to the HPC cluster and how to integrate this functionality with an external web application.
• Introduction to the Model Execution Environment (MEE): The final part of the tutorial will introduce the MEE. We will showcase how MEE streamlines the process of running scientific applications. This will involve:
  • an overview of how to define and manage complex computational workflows.
  • a case study from the InSilicoWorld project, demonstrating how MEE was used to store cohort data and run hundreds of simulations as part of a large-scale computational campaign.

3. Knowledge and skills to be gained

Upon completion of this tutorial, participants will be able to:

• Understand the fundamentals of High-Performance Computing,
• Submit and manage computational jobs on an HPC cluster using the SLURM scheduler,
• Programmatically submit jobs to an HPC cluster via an API,
• Understand the purpose and benefits of the Model Execution Environment (MEE).

Acknowledgements: This tutorial is made possible by the contributions and results from the following projects: EDITH (grant agreement no. 101083771), InSilicoWorld (grant agreement no. 101016503), GEMINI (grant agreement no. 101083771).

References:

Kasztelnik, M. et al. (2023). Digital Twin Simulation Development and Execution on HPC Infrastructures. In: Mikyška, J., de Mulatier, C., Paszyński, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2023. ICCS 2023. Lecture Notes in Computer Science, vol 14074. Springer, Cham. https://doi.org/10.1007/978-3-031-36021-3_2

InSilicoWorld project: https://insilico.world/

EDITH project: https://www.edith-csa.eu

GEMINI project: https://dth-gemini.eu

Sano seminar: Composing Applications In The Model Execution Environment: https://www.youtube.com/watch?v=hFM1jPVAhtg