UNICORN: a deep learning model for integrating multi-stain data in histopathology.

Valentin Koch^1,2, Sabine Bauer^3,4, Shweta Mahajan^1,3, Valerio Lupperger⁵, Michael Joner^3,4, Heribert Schunkert^3,4, Julia A Schnabel^1,2,6, Moritz von Scheidt^3,4, Carsten Marr^7,8,9,10

¹Computational Health Center, Helmholtz Munich - German Research Center for Environmental Health, Munich, Germany.

²School of Computation and Information Technology, Technical University of Munich, Munich, Germany.

³Department of Cardiology, German Heart Centre, TUM University Hospital, Munich, Germany.

⁴DZHK (German Center for Cardiovascular Research), Partner Site Munich Heart Alliance, Munich, Germany.

⁵MLL Munich Leukemia Laboratory, Munich, Germany.

⁶School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.

⁷Computational Health Center, Helmholtz Munich - German Research Center for Environmental Health, Munich, Germany. carsten.marr@helmholtz-munich.de.

⁸Department of Medicine III, Ludwig Maximilian University Hospital, Munich, Germany. carsten.marr@helmholtz-munich.de.

⁹Department of Physics, Ludwig-Maximilians-Universität München, Munich, Germany. carsten.marr@helmholtz-munich.de.

¹⁰DKTK, German Cancer Consortium, Heidelberg, Germany. carsten.marr@helmholtz-munich.de.

PubMed PMC DOI PDF

Abstract

The integration of multi-stain histopathology images through deep learning poses a significant challenge. Current approaches struggle with data heterogeneity and missing data, as concatenating multi-stain features may not effectively model stain-specific and cross-stain interactions. We introduce UNICORN (UNiversal stain Integration network for CORonary classificatioN), a two-stage, end-to-end tra…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.