Spatially resolved transcriptomics and graph-based deep learning improve accuracy of routine CNS tumor diagnostics
The diagnostic landscape of brain tumors integrates comprehensive molecular markers alongside traditional histopathological evaluation. DNA methylation and next-generation sequencing (NGS) have become a cornerstone in central nervous system (CNS) tumor classification. A limiting requirement for NGS and methylation profiling is sufficient DNA quality and quantity, which restrict its feasibility. Here we demonstrate NePSTA (neuropathology spatial transcriptomic analysis) for comprehensive morphological and molecular neuropathological diagnostics from single 5-µm tissue sections. NePSTA uses spatial transcriptomics with graph neural networks for automated histological and molecular evaluations. Trained and evaluated across 130 participants with CNS malignancies and healthy donors across four medical centers, NePSTA predicts tissue histology and methylation-based subclasses with high accuracy. We demonstrate the ability to reconstruct immunohistochemistry and genotype profiling on tissue with minimal requirements, inadequate for conventional molecular diagnostics, demonstrating the potential to enhance tumor subtype identification with implications for fast and precise diagnostic workup.
Authors
- Bhuvic Patel (ORCID: https://orcid.org/0000-0001-8062-7310)
- Moritz Gerstung (ORCID: https://orcid.org/0000-0001-6709-963X)
- Jan Kueckelhaus
- Christina Blume (ORCID: https://orcid.org/0000-0003-1438-9304)
- Christel C. Herold‐Mende (ORCID: https://orcid.org/0000-0002-1915-745X)
- Jasim Kada Benotmane (ORCID: https://orcid.org/0009-0005-2100-913X)
- Oliver Schnell (ORCID: https://orcid.org/0000-0002-1284-1427)
- Yahaya A Yabo (ORCID: https://orcid.org/0000-0002-1128-6038)
- Yiheng Tang (ORCID: https://orcid.org/0000-0002-9484-3353)
- Philipp Sievers (ORCID: https://orcid.org/0000-0003-3237-6021)
- Felix Hinz (ORCID: https://orcid.org/0009-0004-6394-1999)
- Andreas von Deimling (ORCID: https://orcid.org/0000-0002-5863-540X)
- Jürgen Beck (ORCID: https://orcid.org/0000-0002-7687-6098)
- Felix Sahm (ORCID: https://orcid.org/0000-0001-5441-1962)
- Dieter Henrik Heiland (ORCID: https://orcid.org/0000-0002-9258-3033)
- Michael Ritter
- Natalie Berghaus (ORCID: https://orcid.org/0000-0002-5791-698X)
- Zaira Seferbekova (ORCID: https://orcid.org/0000-0002-3131-3697)
- Wolfgang Wick (ORCID: https://orcid.org/0000-0002-6171-634X)
- Areeba Patel (ORCID: https://orcid.org/0000-0003-0374-4227)
- Vidhya Madapusi Ravi (ORCID: https://orcid.org/0000-0003-0062-2099)
- Miriam Ratliff (ORCID: https://orcid.org/0000-0002-9464-6544)
- Junyi Zhang (ORCID: https://orcid.org/0000-0002-0001-2971)
- David Niklas Zimmer
- Giulia Villa (ORCID: https://orcid.org/0000-0003-1120-9638)
- Elena Grabis
- Marcel Seiz‐Rosenhagen
- Amir Khriesh
Institutions
- Northwestern University (US)
- University of Freiburg (DE)
- University of Mannheim (DE)
- German Cancer Research Center (DE)
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Washington University in St. Louis (US)
- Heidelberg University (DE)
- University Medical Center Freiburg (DE)
- University Hospital Heidelberg (DE)
- Universitätsklinikum Erlangen (DE)
- National Center for Tumor Diseases (DE)
- Kernkraftwerk Gundremmingen (DE)
- Neurological Surgery (US)
- Deutsches Konsortium für Translationale Krebsforschung (DE)
Publication Details
- Journal
- Nature Cancer
- Published
- 2025-01-29
- DOI
- https://doi.org/10.1038/s43018-024-00904-z
- Citations
- 19
- Primary Topic
- Glioma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 30.88
Funders
- Friedrich-Alexander-Universität Erlangen-Nürnberg
- Deutsche Forschungsgemeinschaft
- Deutschen Konsortium für Translationale Krebsforschung