1
|
Schumann Y, Dottermusch M, Schweizer L, Krech M, Lempertz T, Schüller U, Neumann P, Neumann JE. Morphology-based molecular classification of spinal cord ependymomas using deep neural networks. Brain Pathol 2024:e13239. [PMID: 38205683 DOI: 10.1111/bpa.13239] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Accepted: 12/31/2023] [Indexed: 01/12/2024] Open
Abstract
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 (nMPE = 84, nSP-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.
Collapse
Affiliation(s)
- Yannis Schumann
- Chair for High Performance Computing, Helmut-Schmidt-University Hamburg, Hamburg, Germany
| | - Matthias Dottermusch
- Center for Molecular Neurobiology (ZMNH), University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany
- Institute of Neuropathology, UKE, Hamburg, Germany
| | - Leonille Schweizer
- 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
| | - Maja Krech
- Institute for Neuropathology, Charité Berlin, Berlin, Germany
| | - Tasja Lempertz
- Center for Molecular Neurobiology (ZMNH), University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany
| | - Ulrich Schüller
- Institute of Neuropathology, UKE, Hamburg, Germany
- Research Institute Children's Cancer Center Hamburg, UKE, Hamburg, Germany
- Department of Pediatric Hematology and Oncology, UKE, Hamburg, Germany
| | - Philipp Neumann
- Chair for High Performance Computing, Helmut-Schmidt-University Hamburg, Hamburg, Germany
| | - Julia E Neumann
- Center for Molecular Neurobiology (ZMNH), University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany
- Institute of Neuropathology, UKE, Hamburg, Germany
| |
Collapse
|
2
|
Sichert A, Le Gall S, Klau LJ, Laillet B, Rogniaux H, Aachmann FL, Hehemann JH. Ion-exchange purification and structural characterization of five sulfated fucoidans from brown algae. Glycobiology 2021; 31:352-357. [PMID: 32651947 PMCID: PMC8091464 DOI: 10.1093/glycob/cwaa064] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2020] [Accepted: 06/30/2020] [Indexed: 12/15/2022] Open
Abstract
Fucoidans are a diverse class of sulfated polysaccharides integral to the cell wall of brown algae, and due to their various bioactivities, they are potential drugs. Standardized work with fucoidans is required for structure-function studies, but remains challenging since available fucoidan preparations are often contaminated with other algal compounds. Additionally, fucoidans are structurally diverse depending on species and season, urging the need for standardized purification protocols. Here, we use ion-exchange chromatography to purify different fucoidans and found a high structural diversity between fucoidans. Ion-exchange chromatography efficiently removes the polysaccharides alginate and laminarin and other contaminants such as proteins and phlorotannins across a broad range of fucoidans from major brown algal orders including Ectocarpales, Laminariales and Fucales. By monomer composition, linkage analysis and NMR characterization, we identified galacturonic acid, glucuronic acid and O-acetylation as new structural features of certain fucoidans and provided a novel structure of fucoidan from Durvillaea potatorum with α-1,3-linked fucose backbone and β-1,6 and β-1,3 galactose branches. This study emphasizes the use of standardized ion-exchange chromatography to obtain defined fucoidans for subsequent molecular studies.
Collapse
Affiliation(s)
- Andreas Sichert
- Max Planck Institute for Marine Microbiology, 28359 Bremen, Germany
- University of Bremen, Center for Marine Environmental Sciences, MARUM, 28359 Bremen, Germany
| | - Sophie Le Gall
- INRAE, UR BIA (Biopolymers Interactions Assemblies), F-44316 Nantes, France
- INRAE, BIBS Facility, F-44316 Nantes, France
| | - Leesa Jane Klau
- Norwegian Biopolymer Laboratory (NOBIPOL), Department of Biotechnology and Food Science, NTNU Norwegian University of Science and Technology, 7491 Trondheim, Norway
| | - Brigitte Laillet
- INRAE, UR BIA (Biopolymers Interactions Assemblies), F-44316 Nantes, France
| | - Hélène Rogniaux
- INRAE, UR BIA (Biopolymers Interactions Assemblies), F-44316 Nantes, France
- INRAE, BIBS Facility, F-44316 Nantes, France
| | - Finn Lillelund Aachmann
- Norwegian Biopolymer Laboratory (NOBIPOL), Department of Biotechnology and Food Science, NTNU Norwegian University of Science and Technology, 7491 Trondheim, Norway
| | - Jan-Hendrik Hehemann
- Max Planck Institute for Marine Microbiology, 28359 Bremen, Germany
- University of Bremen, Center for Marine Environmental Sciences, MARUM, 28359 Bremen, Germany
| |
Collapse
|