Morphology‐based molecular classification of spinal cord ependymomas using deep neural networks
Brain Pathology · 2024-09 · 34 (5)
DOI: 10.1111/bpa.13239 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Pathology, online erschienen am 11.01.2024. Verfasst von Yannis Schumann und 7 weiteren Autor:innen. Beteiligte Einrichtung: Chair for High Performance Computing, Helmut-Schmidt-University Hamburg, Hamburg, Germany. Hauptthemen laut MEDLINE: Ependymoma, Spinal Cord Neoplasms, DNA Methylation, Neural Networks, Computer. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Computational resources (HPC-cluster HSUper) have been provided by the project hpc.bw, funded by dtec.bw-Digitalization and Technology Research Center of the B…, DFG Emmy Noether Program, Fördergemeinschaft Kinderkrebszentrum Hamburg.
Abstract (Originalsprache)
Based on DNA‐methylation, ependymomas growing in the spinal cord comprise two major molecular types termed spinal (SP‐EPN) and myxopapillary ependymomas (MPE(‐A/B)), which differ with respect to their clinical features and prognosis. Due to the existing discrepancy between histomorphogical diagnoses and classification using methylation data, we asked whether deep neural networks can predict the DNA methylation class of spinal cord ependymomas from hematoxylin and eosin stained whole‐slide images. Using explainable AI, we further aimed to prospectively improve the consistency of histology‐based diagnoses with DNA methylation profiling by identifying and quantifying distinct morphological patterns of these molecular ependymoma types. We assembled a case series of 139 molecularly characterized spinal cord ependymomas ( n MPE = 84, n SP‐EPN = 55). Self‐supervised and weakly‐supervised neural networks were used for classification. We employed attention analysis and supervised machine‐learning methods for the discovery and quantification of morphological features and their correlation to the diagnoses of experienced neuropathologists. Our best performing model predicted the DNA methylation class with 98% test accuracy and used self‐supervised learning to outperform pretrained encoder‐networks (86% test accuracy). In contrast, the diagnoses of neuropathologists matched the DNA methylation class in only 83% of cases. Domain‐adaptation techniques improved model generalization to an external validation cohort by up to 22%. Statistically significant morphological features were identified per molecular type and quantitatively correlated to human diagnoses. The approach was extended to recently defined subtypes of myxopapillary ependymomas (MPE‐(A/B), 80% test accuracy). In summary, we demonstrated the accurate prediction of the DNA methylation class of spinal cord ependymomas (SP‐EPN, MPE(‐A/B)) using hematoxylin and eosin stained whole‐slide images. Our approach may prospectively serve as a supplementary resource for integrated diagnostics and may even help to establish a standardized, high‐quality level of histology‐based diagnostics across institutions—in particular in low‐income countries, where expensive DNA‐methylation analyses may not be readily available.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Chair for High Performance Computing, Helmut-Schmidt-University Hamburg, Hamburg, Germany.
- Center for Molecular Neurobiology (ZMNH), University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany.
- Institute of Neuropathology, UKE, Hamburg, Germany.
- Institute of Neurology (Edinger Institute), University Hospital Frankfurt, Goethe University, Frankfurt am Main, Germany.
- German Cancer Consortium (DKTK), Partner Site Frankfurt/Mainz, German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Frankfurt Cancer Institute (FCI), Frankfurt am Main, Germany.
ORCID-Profile: Yannis Schumann, Ulrich Schüller, Philipp Neumann, Julia E Neumann
Förderung
- Computational resources (HPC-cluster HSUper) have been provided by the project hpc.bw, funded by dtec.bw-Digitalization and Technology Research Center of the B…
- DFG Emmy Noether Program
- Fördergemeinschaft Kinderkrebszentrum Hamburg
Zitieren
APA
Schumann, Y., Dottermusch, M., Schweizer, L., Krech, M., Lempertz, T., Schüller, U., Neumann, P., & Neumann, J. E. (2024). Morphology‐based molecular classification of spinal cord ependymomas using deep neural networks. Brain Pathology, 34(5). https://doi.org/10.1111/bpa.13239
Vancouver
Schumann Y, Dottermusch M, Schweizer L, Krech M, Lempertz T, Schüller U, et al. Morphology‐based molecular classification of spinal cord ependymomas using deep neural networks. Brain Pathology. 2024;34(5). doi:10.1111/bpa.13239
BibTeX
@article{Schumann2024,
author = {Schumann, Yannis and Dottermusch, Matthias and Schweizer, Leonille and Krech, Maja and Lempertz, Tasja and Schüller, Ulrich and Neumann, Philipp and Neumann, Julia E},
title = {Morphology‐based molecular classification of spinal cord ependymomas using deep neural networks},
journal = {Brain Pathology},
year = {2024},
volume = {34},
number = {5},
doi = {10.1111/bpa.13239}
}
EUVIMED