MISTAI
MISTAI: Medical Intelligence & Skills Training in AI
Bilateral UKB–Dnipro State Medical University project, funded by the NRW Ministry of Culture and Science, building an AI pipeline and training programme in computational pathology for muscle-invasive bladder cancer.
Abstract
The war in Ukraine has severely disrupted medical research and teaching. Digital pathology and AI offer a way to keep both going without depending on physical infrastructure. MISTAI is a bilateral cooperation between the University Hospital Bonn and Dnipro State Medical University (DSMU), funded by the Ministry of Culture and Science of North Rhine-Westphalia (MKW NRW).
Goals
- Shared data infrastructure: digitise and validate at least 100 H&E and IHC whole-slide images from a DSMU cohort of muscle-invasive bladder cancer (MIBC), on a joint secure platform.
- AI diagnostic pipeline: fine-tune state-of-the-art pathology foundation models on the combined Bonn–Dnipro data, including spatial analysis of tumour-infiltrating lymphocytes from routine H&E slides, inspired by the UC-TIL approach.
- Clinical tool: a QuPath plugin that lets pathologists run the trained model directly in their existing workflow.
- Capacity building: weekly remote collaboration, a one-week exchange visit to Bonn, and a Computational Pathology teaching module for the DSMU curriculum.
- Follow-on work: a joint DFG/BMBF proposal outline and a MICCAI challenge concept.
Partners
Bonn contributes high-resolution slide scanners, AI infrastructure and expertise in computational medical imaging (Prof. Shadi Albarqouni) and translational lung and tumour pathology (Prof. Verena Tischler). DSMU contributes a clinically distinct bladder-cancer cohort and long-standing pathology expertise (Assoc. Prof. Nina Bondarenko, Department of Pathological Anatomy).
Work packages
| WP | Title | Lead | Our role |
|---|---|---|---|
| WP1 | Setup & infrastructure Data-sharing protocol, cloud workspace, federated nodes at both sites, and a validated slide-processing pipeline (July 2026). | UKB | Lead |
| WP2 | Data collection, preparation & annotation Retrospective bladder-cancer cohort from DSMU, H&E and IHC slides digitised in Bonn, quality control, stain normalisation and joint annotation (July – September 2026). | Dnipro | Partner |
| WP3 | Foundation-model fine-tuning & AI development Fine-tuning pathology foundation models (GigaPath, Virchow, CHIEF), spatial tumour-infiltrating-lymphocyte analysis, cross-site federated experiments and a QuPath plugin for pathologists (September – November 2026). | UKB | Lead |
| WP4 | Exchange visit & Computational Pathology Workshop One-week visit of the DSMU team to Bonn, co-located with an open Computational Pathology Workshop (December 2026). | UKB | Lead |
| WP5 | Education module, dissemination & reporting Computational pathology teaching module for DSMU, conference presentations, an open-access manuscript and follow-on proposals (November – December 2026). | Dnipro | Partner |
