1
|
Schweizer L, Seegerer P, Kim HY, Saitenmacher R, Muench A, Barnick L, Osterloh A, Dittmayer C, Jödicke R, Pehl D, Reinhardt A, Ruprecht K, Stenzel W, Wefers AK, Harter PN, Schüller U, Heppner FL, Alber M, Müller KR, Klauschen F. Analysing cerebrospinal fluid with explainable deep learning: From diagnostics to insights. Neuropathol Appl Neurobiol 2023; 49:e12866. [PMID: 36519297 DOI: 10.1111/nan.12866] [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] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2022] [Revised: 11/14/2022] [Accepted: 12/13/2022] [Indexed: 12/23/2022]
Abstract
AIM Analysis of cerebrospinal fluid (CSF) is essential for diagnostic workup of patients with neurological diseases and includes differential cell typing. The current gold standard is based on microscopic examination by specialised technicians and neuropathologists, which is time-consuming, labour-intensive and subjective. METHODS We, therefore, developed an image analysis approach based on expert annotations of 123,181 digitised CSF objects from 78 patients corresponding to 15 clinically relevant categories and trained a multiclass convolutional neural network (CNN). RESULTS The CNN classified the 15 categories with high accuracy (mean AUC 97.3%). By using explainable artificial intelligence (XAI), we demonstrate that the CNN identified meaningful cellular substructures in CSF cells recapitulating human pattern recognition. Based on the evaluation of 511 cells selected from 12 different CSF samples, we validated the CNN by comparing it with seven board-certified neuropathologists blinded for clinical information. Inter-rater agreement between the CNN and the ground truth was non-inferior (Krippendorff's alpha 0.79) compared with the agreement of seven human raters and the ground truth (mean Krippendorff's alpha 0.72, range 0.56-0.81). The CNN assigned the correct diagnostic label (inflammatory, haemorrhagic or neoplastic) in 10 out of 11 clinical samples, compared with 7-11 out of 11 by human raters. CONCLUSIONS Our approach provides the basis to overcome current limitations in automated cell classification for routine diagnostics and demonstrates how a visual explanation framework can connect machine decision-making with cell properties and thus provide a novel versatile and quantitative method for investigating CSF manifestations of various neurological diseases.
Collapse
Affiliation(s)
- Leonille Schweizer
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Philipp Seegerer
- Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technische Universität Berlin, Berlin, Germany.,Aignostics GmbH, Berlin, Germany
| | - Hee-Yeong Kim
- Systems Medicine of Infectious Disease, Robert Koch Institute, Berlin, Germany
| | - René Saitenmacher
- Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technische Universität Berlin, Berlin, Germany
| | - Amos Muench
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Liane Barnick
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Anja Osterloh
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Carsten Dittmayer
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Ruben Jödicke
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Debora Pehl
- Department of Pathology, Vivantes Hospitals Berlin, Berlin, Germany
| | | | - Klemens Ruprecht
- Department of Neurology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Werner Stenzel
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Annika K Wefers
- Institute of NeuropathologyUniversity Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Patrick N Harter
- Neurological Institute (Edinger Institute), Goethe University, Frankfurt am Main, Germany.,Frankfurt Cancer Institute, Goethe University, Frankfurt am Main, Germany.,German Cancer Consortium (DKTK), Partner Site Frankfurt/Mainz, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Ulrich Schüller
- Institute of NeuropathologyUniversity Medical Center Hamburg-Eppendorf, Hamburg, Germany.,Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.,Research Institute Children's Cancer Center Hamburg, Hamburg, Germany
| | - Frank L Heppner
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany.,Cluster of Excellence, NeuroCure, Berlin, Germany.,German Center for Neurodegenerative Diseases (DZNE) Berlin, Berlin, Germany
| | - Maximilian Alber
- Aignostics GmbH, Berlin, Germany.,Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | - Klaus-Robert Müller
- Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technische Universität Berlin, Berlin, Germany.,Max Planck Institut für Informatik, Saarbrücken, Germany.,Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Germany.,Department of Artificial Intelligence, Korea University, Seoul, South Korea
| | - Frederick Klauschen
- Berlin Institute for the Foundations of Learning and Data (BIFOLD), Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), Heidelberg, Germany.,Institute of Pathology, Ludwig-Maximilians-Universität München, Munich, Germany
| |
Collapse
|