Periodic Reporting for period 1 - BioMedAI TWINNING (BioMedAI TWINNING)
Reporting period: 2022-11-01 to 2025-10-31
Rising demand for advanced clinical diagnostics is outpacing current capacity. BioMedAI addresses this by building an infrastructure where computer scientists and clinicians jointly develop semi-automated, explainable and trustworthy AI for diagnostics. The project links Masaryk University (MU) and Masaryk Memorial Cancer Institute (MMCI) with advanced partners Medical University of Graz (MUG) and TU Berlin (TUB), leveraging expertise in secure processing of sensitive image/clinical data, human-in-the-loop methods, and clinical validation. Core activities focus on training MU and MMCI staff through thematic workshops, hands-on virtual training, and summer/winter schools: one on XAI for medical imaging and clinical data, and one on FAIR management of sensitive medical data. BioMedAI also strengthens visibility and sustainability by training a PR manager for stakeholder communication and upskilling project management teams in competitive grant writing.
Scientific collaboration in BioMedAI was significantly strengthened, leading to multiple proposal submissions and several funded follow-ups, including RI-SCALE (Horizon Europe), an AZV project with IKEM, and a GAČR project. A concrete result was the cross-institutional MU–MUG XAI development team focused on FAIRification and management of large digital pathology collections and on developing AI models for medical applications. Collaboration expanded beyond the consortium (e.g. Faculty Hospital St. Anna Brno, IKEM Prague). At MU, the affiliated RationAI laboratory expanded and introduced a clearer leadership structure for efficient mentoring and talent development. The project also catalysed the creation of the AigoPath startup and strengthened industry partnerships (Magicware, Carebot, Comprimato) and strategic collaboration with EMPAIA (via TUB), increasing visibility and access to international networks.
A major practical output is the Educational XAI Toolkit: RatioPath (libraries, tools and templates for digital pathology ML/XAI), RatioVis (interactive experiment reporting and visualization over whole-slide images via the xOpat WSI viewer and an MLflow dashboard), and RatioCast (AI time-series forecasting integrated with SensitiveCloud and tested on blood biomarker data). The toolkit was applied in multiple digital pathology use cases, including prostate cancer (detection and Gleason scoring), colorectal cancer, and breast cancer (Ki-67 scoring). Input data quality control proved critical; AI and non-AI QC/QA methods were implemented as pre-training gates and integrated into the pipelines.
Secure infrastructure for sensitive data was established through migration to the ISO 27001-certified, Kubernetes-based SensitiveCloud at MU (CERIT-SC) and porting RatioPath/RatioVis accordingly. Data management mechanisms ensured strict separation of institutional datasets, controlled access, auditability, and reproducible workflows for pseudonymized WSI used in infrastructure development, pipeline testing, and partner training. A privacy risk model was introduced to systematically assess and mitigate disclosure and re-identification risks and to guide technical/organizational controls. The Data Management Plan (GDPR, FAIR, FAIR-Health) was updated twice and informed a future-proof concept for integrated management of clinical, histopathological and imaging data.
Training and knowledge transfer were delivered through two Summer Schools on explainable AI (expert talks plus extensive hands-on sessions) and a joint Brno–Graz Winter School extending XAI with NLP/LLM methods for structured extraction from clinical datasets. Additional workshops and trainings covered data generation/extraction, annotation workflows, and QA for both pathologists and AI researchers. Junior pathologists and students were trained to review and annotate data, enabling MMCI testing of prostate cancer prototype diagnostic support. Continuous training in FAIR/FAIR-Health data management and sensitive data handling supported the jointly developed tissue classification system, which underpins anonymized digital pathology archives intended for sharing via BBMRI.
A major practical output is the Educational XAI Toolkit: RatioPath (libraries, tools and templates for digital pathology ML/XAI), RatioVis (interactive experiment reporting and visualization over whole-slide images via the xOpat WSI viewer and an MLflow dashboard), and RatioCast (AI time-series forecasting integrated with SensitiveCloud and tested on blood biomarker data). The toolkit was applied in multiple digital pathology use cases, including prostate cancer (detection and Gleason scoring), colorectal cancer, and breast cancer (Ki-67 scoring). Input data quality control proved critical; AI and non-AI QC/QA methods were implemented as pre-training gates and integrated into the pipelines.
Secure infrastructure for sensitive data was established through migration to the ISO 27001-certified, Kubernetes-based SensitiveCloud at MU (CERIT-SC) and porting RatioPath/RatioVis accordingly. Data management mechanisms ensured strict separation of institutional datasets, controlled access, auditability, and reproducible workflows for pseudonymized WSI used in infrastructure development, pipeline testing, and partner training. A privacy risk model was introduced to systematically assess and mitigate disclosure and re-identification risks and to guide technical/organizational controls. The Data Management Plan (GDPR, FAIR, FAIR-Health) was updated twice and informed a future-proof concept for integrated management of clinical, histopathological and imaging data.
Training and knowledge transfer were delivered through two Summer Schools on explainable AI (expert talks plus extensive hands-on sessions) and a joint Brno–Graz Winter School extending XAI with NLP/LLM methods for structured extraction from clinical datasets. Additional workshops and trainings covered data generation/extraction, annotation workflows, and QA for both pathologists and AI researchers. Junior pathologists and students were trained to review and annotate data, enabling MMCI testing of prostate cancer prototype diagnostic support. Continuous training in FAIR/FAIR-Health data management and sensitive data handling supported the jointly developed tissue classification system, which underpins anonymized digital pathology archives intended for sharing via BBMRI.
Impacts are structured in four categories:
Scientific: BioMedAI established a “symbiotic group” (MU, MUG, MMCI, TUB) able to address complex, day-to-day challenges in digital pathology and XAI. Contributions to the EOSC MCVAL demonstrator under BBMRI coordination position the consortium as a key player in European federated research. This is reinforced by successful follow-up funding, including RI-SCALE (Horizon Europe) involving consortium members.
Economic/Commercial: The AigoPath start-up was created to exploit project results, including the xOpat viewer and related AI solutions. Partnerships with industry (e.g. Carebot, Magicware) support translation into deployable healthcare applications.
Societal/Educational: Capacity building was advanced through Summer and Winter Schools and associated trainings, including over 60 student researchers trained at MU alone. Workshops, training sessions and public presentations improved end-user (pathologist) understanding of digital pathology, data collection, and workflow integration.
Clinical: A prototype diagnostic system based on the Educational XAI toolkit demonstrated time-saving potential and decision support; a cancer-detection prototype was practically trialled on datasets from 50+ patients.
Key needs for future success:
• Clinical validation & regulation: broader testing and progress towards compliance with relevant certification (e.g. IVDR) to enable routine clinical use.
• Infrastructure sustainability: continued operation of BioMedAI management structures and the SensitiveCloud environment.
• Internationalisation & standardisation: ongoing engagement with EMPAIA, EOSC, ESDIP and ISO; notably, digital pathology pilots based on the RatioPath XAI toolkit contributed as validators to the ISO 23494 series development.
Scientific: BioMedAI established a “symbiotic group” (MU, MUG, MMCI, TUB) able to address complex, day-to-day challenges in digital pathology and XAI. Contributions to the EOSC MCVAL demonstrator under BBMRI coordination position the consortium as a key player in European federated research. This is reinforced by successful follow-up funding, including RI-SCALE (Horizon Europe) involving consortium members.
Economic/Commercial: The AigoPath start-up was created to exploit project results, including the xOpat viewer and related AI solutions. Partnerships with industry (e.g. Carebot, Magicware) support translation into deployable healthcare applications.
Societal/Educational: Capacity building was advanced through Summer and Winter Schools and associated trainings, including over 60 student researchers trained at MU alone. Workshops, training sessions and public presentations improved end-user (pathologist) understanding of digital pathology, data collection, and workflow integration.
Clinical: A prototype diagnostic system based on the Educational XAI toolkit demonstrated time-saving potential and decision support; a cancer-detection prototype was practically trialled on datasets from 50+ patients.
Key needs for future success:
• Clinical validation & regulation: broader testing and progress towards compliance with relevant certification (e.g. IVDR) to enable routine clinical use.
• Infrastructure sustainability: continued operation of BioMedAI management structures and the SensitiveCloud environment.
• Internationalisation & standardisation: ongoing engagement with EMPAIA, EOSC, ESDIP and ISO; notably, digital pathology pilots based on the RatioPath XAI toolkit contributed as validators to the ISO 23494 series development.