AI cytometry resources

ESCCA 2026 poster. A real-world multicenter evaluation of AI-assisted leukocyte population identification, run with the Laboratorio Especializado de Hematología at Hospital Dr. Rafael Ángel Calderón Guardia (CCSS) in Costa Rica, the HpH Institut für Pathologie und Hämatopathologie Hamburg and Pathodiagnostik Berlin MVZ GmbH.

The study asks whether one AI model, trained predominantly on Western European cohorts, keeps its accuracy across different laboratories, panels, workflows, sample types and patient populations. The same model was applied retrospectively at all three sites, with no site-specific retraining and no panel-specific optimization.

• 7,039 samples across three laboratories in two countries
• Excellent concordance for 8 of 9 shared populations, with Pearson ρ from 0.93 to 1.00
• Pooled linear-fit slopes from 0.93 to 1.13, near unity
• High agreement against both routine clinical differential counts and expert manual gating
• Monocyte identification was the only population with reduced agreement

View the full poster or download it as a PDF.

The AI model is hema.to CellStudio (RUO): a proprietary transformer-based neural network trained from scratch on thousands of expert-annotated flow-cytometry files. Research use only; not for use in diagnostic procedures.

ESMO AI 2025 poster. This work on AI cytometry was led by hema.to’s partners at the HpH Institut für Pathologie und Hämatopathologie Hamburg and Pathodiagnostik Berlin MVZ GmbH.

The retrospective comparison across more than 6,500 peripheral-blood samples shows high concordance with conventional laboratory results across major subpopulations, robustness across multiple panels, workflows, and laboratory locations, and where further harmonization is needed.

Download the full poster.

hema.to has closed a €3.6 million financing round led by LUMO Labs, an impact-driven Dutch venture capital firm. This financing will help hema.to pursue product-market fit for its clinical-grade AI software for blood cancer and other cytometry-based blood tests.

hema.to’s committed investors include Elaia and Clément Vanden Driessche, Heal Capital and Christian Lautner, HTGF | High-Tech Gründerfonds and Dr. Nik Raupp, Labor Becker MVZ eGbR, Marc Becker, Malte von Trotha, and angel investor Thomas Henkel.

New investors include Bayern Kapital and Matthias Buchinger, Cross Atlantic Angels with Jens Weitzel and Niklas Herriger, and Akwa Group with Pim Hollestelle and Thomas Hannes.

The round strengthens hema.to’s work to build innovative cytometry technology that supports earlier diagnoses and better treatment decisions.

hema.to’s AI model combines supervised and clustering approaches to detect small pathological B-cell populations in blood and bone marrow samples. Key features include:

• Efficient identification of populations as small as 3% of total cells
• Differentiation of six B-cell neoplasms: CLL, MCL, HCL, FL, MZL, and DLBCL
• Detection of previously unnoticed secondary B-NHL clones
• Optimization for a low false-negative rate, enabling fast, automated screening

The model offers systematic, rapid analysis to aid clinical B-cell neoplasm flow cytometry. View the full poster.

In May, hema.to closed its seed round with Elaia Partners, Heal Capital, and HTGF to bring precision diagnostics to immune medicine.

Elaia Managing Partner Anne-Sophie Carrese said that the founding team’s entrepreneurial and research experience, together with hema.to’s plans to scale its go-to-market strategy, fit Elaia’s deep-tech seed investment thesis.

Read the press release on tech.eu.

hema.to achieved FDA compliance as a Class I device less than four months after receiving its CE mark. This was made possible by hema.to’s team and regulatory partners, including QServe Group, Jennifer Hadfield, and Be-on-Quality.

The photo shows Aleks and Jennifer registering the device; the FDA sent the good news the following day.

hema.to was clinically validated in an international, four-center clinical study. Blood cancer diagnoses were made twice as fast and at clinical grade with support from hema.to’s decision-support software.

Download the press release.

Clinical study white paper. hema.to was clinically validated in an international, four-center clinical trial. Blood cancer diagnoses were made twice as fast, with 8% more sensitivity and 10% more specificity, using hema.to’s decision-support software.

Download the white paper.

hema.to won first prize at the Medical Innovation Night in Nürnberg. The jury included Medical Valley EMN e. V., Siemens Healthineers, aescuvest, GWQ ServicePlus AG, IONOS, and Fraunhofer IIS.

The €20,000 prize supports hema.to’s exploration of partnerships with GWQ and Siemens Healthineers.

hema.to achieved compliance with the IVDD. The company conforms to ISO 13485 for quality management, ISO 14971 for risk management, ISO 62366 for usability, ISO 62304 for software life-cycle management, and IEC 82304 for health software.

Cell Patterns paper. Nanditha Mallesh and co-authors describe how knowledge transfer enhances AI performance in Cell Patterns.

The collaboration between hema.to’s team, the Munich Leukemia Lab, Charité, and additional university clinics showed that data from multiple laboratories can be combined to increase the clinical performance of AI models for each laboratory.

Cytometry A paper. hema.to’s team collaborated with experienced hematologists and the University of Bonn on this Cytometry A study.

Zhao et al. showed that deep learning can aid routine clinical workflows using cytometry data.

Blood paper II. Nanditha Mallesh and co-authors presented this 2019 Blood paper.

The study showed that combining multiple datasets improves diagnostic performance through an approach called “knowledge transfer.”

Blood paper I. A collaboration between hema.to, the Munich Leukemia Lab, and the University of Bonn produced this 2019 Blood paper.

The paper shows that AI can support hematologists in routine blood cancer diagnosis workflows by providing highly reliable recommendations.