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
|
2
|
Jurmeister P, Glöß S, Roller R, Leitheiser M, Schmid S, Mochmann LH, Payá Capilla E, Fritz R, Dittmayer C, Friedrich C, Thieme A, Keyl P, Jarosch A, Schallenberg S, Bläker H, Hoffmann I, Vollbrecht C, Lehmann A, Hummel M, Heim D, Haji M, Harter P, Englert B, Frank S, Hench J, Paulus W, Hasselblatt M, Hartmann W, Dohmen H, Keber U, Jank P, Denkert C, Stadelmann C, Bremmer F, Richter A, Wefers A, Ribbat-Idel J, Perner S, Idel C, Chiariotti L, Della Monica R, Marinelli A, Schüller U, Bockmayr M, Liu J, Lund VJ, Forster M, Lechner M, Lorenzo-Guerra SL, Hermsen M, Johann PD, Agaimy A, Seegerer P, Koch A, Heppner F, Pfister SM, Jones DTW, Sill M, von Deimling A, Snuderl M, Müller KR, Forgó E, Howitt BE, Mertins P, Klauschen F, Capper D. DNA methylation-based classification of sinonasal tumors. Nat Commun 2022; 13:7148. [PMID: 36443295 PMCID: PMC9705411 DOI: 10.1038/s41467-022-34815-3] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2022] [Accepted: 11/07/2022] [Indexed: 11/29/2022] Open
Abstract
The diagnosis of sinonasal tumors is challenging due to a heterogeneous spectrum of various differential diagnoses as well as poorly defined, disputed entities such as sinonasal undifferentiated carcinomas (SNUCs). In this study, we apply a machine learning algorithm based on DNA methylation patterns to classify sinonasal tumors with clinical-grade reliability. We further show that sinonasal tumors with SNUC morphology are not as undifferentiated as their current terminology suggests but rather reassigned to four distinct molecular classes defined by epigenetic, mutational and proteomic profiles. This includes two classes with neuroendocrine differentiation, characterized by IDH2 or SMARCA4/ARID1A mutations with an overall favorable clinical course, one class composed of highly aggressive SMARCB1-deficient carcinomas and another class with tumors that represent potentially previously misclassified adenoid cystic carcinomas. Our findings can aid in improving the diagnostic classification of sinonasal tumors and could help to change the current perception of SNUCs.
Collapse
Affiliation(s)
- Philipp Jurmeister
- grid.411095.80000 0004 0477 2585Institute of Pathology, Ludwig Maximilians University Hospital Munich, Munich, Germany ,grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany ,grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.7497.d0000 0004 0492 0584 German Cancer Consortium (DKTK), Partner Site Munich, and German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Stefanie Glöß
- grid.6363.00000 0001 2218 4662Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Neuropathology, Charitéplatz 1, Berlin, Germany
| | - Renée Roller
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany ,grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.484013.a0000 0004 6879 971XProteomics Platform, Berlin Institute of Health (BIH) and Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), 13125 Berlin, Germany
| | - Maximilian Leitheiser
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Simone Schmid
- grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.6363.00000 0001 2218 4662Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Neuropathology, Charitéplatz 1, Berlin, Germany
| | - Liliana H. Mochmann
- grid.411095.80000 0004 0477 2585Institute of Pathology, Ludwig Maximilians University Hospital Munich, Munich, Germany
| | - Emma Payá Capilla
- grid.411095.80000 0004 0477 2585Institute of Pathology, Ludwig Maximilians University Hospital Munich, Munich, Germany
| | - Rebecca Fritz
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Carsten Dittmayer
- grid.6363.00000 0001 2218 4662Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Neuropathology, Charitéplatz 1, Berlin, Germany
| | - Corinna Friedrich
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany ,grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.419491.00000 0001 1014 0849MDC Graduate School, Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany ,grid.7468.d0000 0001 2248 7639Humboldt Universität zu Berlin, Institute of Chemistry, Berlin, Germany
| | - Anne Thieme
- grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.6363.00000 0001 2218 4662Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Neuropathology, Charitéplatz 1, Berlin, Germany
| | - Philipp Keyl
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Armin Jarosch
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Simon Schallenberg
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Hendrik Bläker
- grid.411339.d0000 0000 8517 9062Institute of Pathology, University Hospital Leipzig, Leipzig, Germany
| | - Inga Hoffmann
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Claudia Vollbrecht
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany ,grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Annika Lehmann
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Michael Hummel
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany ,grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Daniel Heim
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Mohamed Haji
- grid.484013.a0000 0004 6879 971XProteomics Platform, Berlin Institute of Health (BIH) and Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), 13125 Berlin, Germany
| | - Patrick Harter
- grid.7497.d0000 0004 0492 0584 German Cancer Consortium (DKTK), Partner Site Munich, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.7839.50000 0004 1936 9721Institute of Neurology (Edinger Institute), Goethe-University Frankfurt am Main, Frankfurt am Main, Germany ,grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Frankfurt/Mainz, Frankfurt am Main, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Benjamin Englert
- grid.411095.80000 0004 0477 2585Institute of Neuropathology, Ludwig Maximilians University Hospital Munich, Munich, Germany
| | - Stephan Frank
- grid.410567.1Department of Neuropathology, Institute of Pathology, Basel University Hospital, Basel, Switzerland
| | - Jürgen Hench
- grid.410567.1Department of Neuropathology, Institute of Pathology, Basel University Hospital, Basel, Switzerland
| | - Werner Paulus
- grid.16149.3b0000 0004 0551 4246Institute of Neuropathology, University Hospital Münster, Münster, Germany
| | - Martin Hasselblatt
- grid.16149.3b0000 0004 0551 4246Institute of Neuropathology, University Hospital Münster, Münster, Germany
| | - Wolfgang Hartmann
- grid.16149.3b0000 0004 0551 4246Division of Translational Pathology, Gerhard-Domagk-Institute of Pathology, University Hospital Münster, Münster, Germany
| | - Hildegard Dohmen
- grid.8664.c0000 0001 2165 8627Institute of Neuropathology, University of Giessen, Giessen, Germany
| | - Ursula Keber
- grid.10253.350000 0004 1936 9756Institute of Neuropathology, Philipps-University, Marburg, Germany
| | - Paul Jank
- grid.10253.350000 0004 1936 9756Institute of Pathology, Philipps-University Marburg and University Hospital Marburg, Marburg, Germany
| | - Carsten Denkert
- grid.10253.350000 0004 1936 9756Institute of Pathology, Philipps-University Marburg and University Hospital Marburg, Marburg, Germany
| | - Christine Stadelmann
- grid.411984.10000 0001 0482 5331Institute for Neuropathology, University Medical Centre Göttingen, Göttingen, Germany
| | - Felix Bremmer
- grid.411984.10000 0001 0482 5331Institute of Pathology, University Medical Center, Göttingen, Germany
| | - Annika Richter
- grid.411984.10000 0001 0482 5331Institute of Pathology, University Medical Center, Göttingen, Germany
| | - Annika Wefers
- grid.5253.10000 0001 0328 4908Department of Neuropathology, University Hospital Heidelberg, Heidelberg, Germany ,grid.7497.d0000 0004 0492 0584Clinical Cooperation Unit Neuropathology, German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.13648.380000 0001 2180 3484Institute of Neuropathology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Julika Ribbat-Idel
- Institute of Pathology, University of Luebeck and University Hospital Schleswig-Holstein, Campus Luebeck, Luebeck, Germany
| | - Sven Perner
- Institute of Pathology, University of Luebeck and University Hospital Schleswig-Holstein, Campus Luebeck, Luebeck, Germany ,grid.418187.30000 0004 0493 9170Pathology, Research Center Borstel, Leibniz Lung Center, Borstel, Germany ,grid.452624.3German Center for Lung Research (DZL), Partner Site Luebeck, Luebeck, Germany
| | - Christian Idel
- grid.412468.d0000 0004 0646 2097Department of Otorhinolaryngology, University Hospital Schleswig-Holstein, Campus Lübeck, Lübeck, Germany
| | - Lorenzo Chiariotti
- grid.4691.a0000 0001 0790 385XDipartimento di Medicina Molecolare e Biotecnologie Mediche, Università degli Studi di Napoli Federico II, Via S. Pansini 5, 80131 Naples, Italy ,grid.4691.a0000 0001 0790 385XCEINGE Biotecnologie Avanzate, 80145 Naples, Italy
| | - Rosa Della Monica
- grid.4691.a0000 0001 0790 385XCEINGE Biotecnologie Avanzate, 80145 Naples, Italy
| | - Alfredo Marinelli
- grid.4691.a0000 0001 0790 385XDepartment of Medicina Clinica e Chirurgia, University Federico II, Naples, Italy
| | - Ulrich Schüller
- grid.13648.380000 0001 2180 3484Institute of Neuropathology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany ,grid.13648.380000 0001 2180 3484Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany ,grid.470174.1Research Institute Children’s Cancer Center Hamburg, Hamburg, Germany
| | - Michael Bockmayr
- grid.6363.00000 0001 2218 4662Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany ,grid.13648.380000 0001 2180 3484Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany ,grid.470174.1Research Institute Children’s Cancer Center Hamburg, Hamburg, Germany
| | - Jacklyn Liu
- grid.83440.3b0000000121901201UCL Cancer Institute, University College London, 72 Huntley Street, London, WC1E 6BT UK ,grid.83440.3b0000000121901201UCL Academic Head and Neck Centre, Division of Surgery and Interventional Science, University College London, London, UK
| | - Valerie J. Lund
- grid.83440.3b0000000121901201UCL Cancer Institute, University College London, 72 Huntley Street, London, WC1E 6BT UK ,grid.83440.3b0000000121901201UCL Academic Head and Neck Centre, Division of Surgery and Interventional Science, University College London, London, UK
| | - Martin Forster
- grid.83440.3b0000000121901201UCL Cancer Institute, University College London, 72 Huntley Street, London, WC1E 6BT UK ,grid.83440.3b0000000121901201UCL Academic Head and Neck Centre, Division of Surgery and Interventional Science, University College London, London, UK
| | - Matt Lechner
- grid.83440.3b0000000121901201UCL Cancer Institute, University College London, 72 Huntley Street, London, WC1E 6BT UK ,grid.83440.3b0000000121901201UCL Academic Head and Neck Centre, Division of Surgery and Interventional Science, University College London, London, UK
| | - Sara L. Lorenzo-Guerra
- grid.511562.4Department of Head and Neck Oncology, Instituto de Investigación Sanitaria del Principado de Asturias (ISPA), Oviedo, Spain
| | - Mario Hermsen
- grid.511562.4Department of Head and Neck Oncology, Instituto de Investigación Sanitaria del Principado de Asturias (ISPA), Oviedo, Spain
| | - Pascal D. Johann
- Swabian Childrens’ Cancer Center, University Childrens’ Hospital Augsburg and EU-RHAB Registry, Augsburg, Germany
| | - Abbas Agaimy
- grid.411668.c0000 0000 9935 6525Institute of Pathology, Friedrich-Alexander-University Erlangen-Nürnberg, University Hospital, Erlangen, Germany
| | - Philipp Seegerer
- grid.6734.60000 0001 2292 8254Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technical University of Berlin, Berlin, Germany
| | - Arend Koch
- grid.6363.00000 0001 2218 4662Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Neuropathology, Charitéplatz 1, Berlin, Germany
| | - Frank Heppner
- grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.6363.00000 0001 2218 4662Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Neuropathology, Charitéplatz 1, Berlin, Germany
| | - Stefan M. Pfister
- grid.510964.fHopp Children’s Cancer Center Heidelberg (KiTZ), Heidelberg, Germany ,grid.7497.d0000 0004 0492 0584Division of Pediatric Neurooncology, German Cancer Research Center (DKFZ) and German Cancer Consortium (DKTK), Heidelberg, Germany ,grid.5253.10000 0001 0328 4908Department of Hematology and Oncology, Heidelberg University Hospital, Heidelberg, Germany
| | - David T. W. Jones
- grid.510964.fHopp Children’s Cancer Center Heidelberg (KiTZ), Heidelberg, Germany ,grid.7497.d0000 0004 0492 0584Division of Pediatric Glioma Research, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Martin Sill
- grid.510964.fHopp Children’s Cancer Center Heidelberg (KiTZ), Heidelberg, Germany
| | - Andreas von Deimling
- grid.5253.10000 0001 0328 4908Department of Neuropathology, University Hospital Heidelberg, Heidelberg, Germany ,grid.7497.d0000 0004 0492 0584Clinical Cooperation Unit Neuropathology, German Cancer Consortium (DKTK), German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Matija Snuderl
- grid.240324.30000 0001 2109 4251Division of Neuropathology, NYU Langone Health, New York, USA ,grid.240324.30000 0001 2109 4251Laura and Isaac Perlmutter Cancer Center, NYU Langone Health, New York, USA ,grid.240324.30000 0001 2109 4251Division of Molecular Pathology and Diagnostics, NYU Langone Health, New York, USA
| | - Klaus-Robert Müller
- grid.6734.60000 0001 2292 8254Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technical University of Berlin, Berlin, Germany ,grid.222754.40000 0001 0840 2678Department of Artificial Intelligence, Korea University, Seoul, South Korea ,grid.419528.30000 0004 0491 9823Max-Planck-Institute for Informatics, Saarbrücken, Germany ,BIFOLD – Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
| | - Erna Forgó
- grid.168010.e0000000419368956Stanford University School of Medicine, Stanford, CA USA
| | - Brooke E. Howitt
- grid.168010.e0000000419368956Stanford University School of Medicine, Stanford, CA USA
| | - Philipp Mertins
- grid.484013.a0000 0004 6879 971XProteomics Platform, Berlin Institute of Health (BIH) and Max Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), 13125 Berlin, Germany
| | - Frederick Klauschen
- grid.411095.80000 0004 0477 2585Institute of Pathology, Ludwig Maximilians University Hospital Munich, Munich, Germany ,grid.7497.d0000 0004 0492 0584 German Cancer Consortium (DKTK), Partner Site Munich, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,BIFOLD – Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
| | - David Capper
- grid.7497.d0000 0004 0492 0584German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany ,grid.6363.00000 0001 2218 4662Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Department of Neuropathology, Charitéplatz 1, Berlin, Germany
| |
Collapse
|
3
|
Leitheiser M, Capper D, Seegerer P, Lehmann A, Schüller U, Müller KR, Klauschen F, Jurmeister P, Bockmayr M. Machine Learning Models Predict the Primary Sites of Head and Neck Squamous Cell Carcinoma Metastases Based on DNA Methylation. J Pathol 2021; 256:378-387. [PMID: 34878655 DOI: 10.1002/path.5845] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [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: 07/26/2021] [Revised: 10/24/2021] [Accepted: 12/06/2021] [Indexed: 11/10/2022]
Abstract
In head and neck squamous cell cancers (HNSCs) that present as metastases with an unknown primary (HNSC-CUPs), the identification of a primary tumor improves therapy options and increases patient survival. However, the currently available diagnostic methods are laborious and do not offer a sufficient detection rate. Predictive machine learning models based on DNA methylation profiles have recently emerged as a promising technique for tumor classification. We applied this technique to HNSC to develop a tool that can improve the diagnostic workup for HNSC-CUPs. On a reference cohort of 405 primary HNSC samples, we developed four classifiers based on different machine learning models (random forest (RF), neural network (NN), elastic net penalized logistic regression (LOGREG), support vector machine (SVM)) that predict the primary site of HNSC tumors from their DNA methylation profile. The classifiers achieved high classification accuracies (RF=83%, NN=88%, LOGREG=SVM=89%) on an independent cohort of 64 HNSC metastases. Further, the NN, LOGREG, and SVM models significantly outperformed p16 status as a marker for an origin in the oropharynx. In conclusion, the DNA methylation profiles of HNSC metastases are characteristic for their primary sites and the classifiers developed in this study, which are made available to the scientific community, can provide valuable information to guide the diagnostic workup of HNSC-CUP. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Maximilian Leitheiser
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Institute of Pathology, Berlin, Germany
| | - David Capper
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, 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, Technical University of Berlin, Berlin, Germany.,Aignostics GmbH, Berlin, Germany
| | - Annika Lehmann
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Institute of Pathology, Berlin, Germany
| | - Ulrich Schüller
- Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.,Institute of Neuropathology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.,Research Institute Children's Cancer Center Hamburg, Hamburg, Germany
| | - Klaus-Robert Müller
- Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technical University of Berlin, Berlin, Germany.,Department of Artificial Intelligence, Korea University, Seoul, South Korea.,Max-Planck-Institute for Informatics, Saarbrücken, Germany.,BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
| | - Frederick Klauschen
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Institute of Pathology, Berlin, Germany.,Aignostics GmbH, Berlin, Germany.,BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany.,LMU München, Institute of Pathology, Faculty of Medicine, LMU Munich, Munich, Germany
| | - Philipp Jurmeister
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Institute of Pathology, Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Berlin, German Cancer Research Center (DKFZ), Heidelberg, Germany.,LMU München, Institute of Pathology, Faculty of Medicine, LMU Munich, Munich, Germany
| | - Michael Bockmayr
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Institute of Pathology, Berlin, Germany.,Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.,Research Institute Children's Cancer Center Hamburg, Hamburg, Germany.,Mildred Scheel Cancer Career Center HaTriCS4, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| |
Collapse
|
4
|
Jurmeister P, Bockmayr M, Seegerer P, Bockmayr T, Treue D, Montavon G, Vollbrecht C, Arnold A, Teichmann D, Bressem K, Schüller U, von Laffert M, Müller KR, Capper D, Klauschen F. Machine learning analysis of DNA methylation profiles distinguishes primary lung squamous cell carcinomas from head and neck metastases. Sci Transl Med 2020; 11:11/509/eaaw8513. [PMID: 31511427 DOI: 10.1126/scitranslmed.aaw8513] [Citation(s) in RCA: 73] [Impact Index Per Article: 18.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2019] [Accepted: 08/22/2019] [Indexed: 12/22/2022]
Abstract
Head and neck squamous cell carcinoma (HNSC) patients are at risk of suffering from both pulmonary metastases or a second squamous cell carcinoma of the lung (LUSC). Differentiating pulmonary metastases from primary lung cancers is of high clinical importance, but not possible in most cases with current diagnostics. To address this, we performed DNA methylation profiling of primary tumors and trained three different machine learning methods to distinguish metastatic HNSC from primary LUSC. We developed an artificial neural network that correctly classified 96.4% of the cases in a validation cohort of 279 patients with HNSC and LUSC as well as normal lung controls, outperforming support vector machines (95.7%) and random forests (87.8%). Prediction accuracies of more than 99% were achieved for 92.1% (neural network), 90% (support vector machine), and 43% (random forest) of these cases by applying thresholds to the resulting probability scores and excluding samples with low confidence. As independent clinical validation of the approach, we analyzed a series of 51 patients with a history of HNSC and a second lung tumor, demonstrating the correct classifications based on clinicopathological properties. In summary, our approach may facilitate the reliable diagnostic differentiation of pulmonary metastases of HNSC from primary LUSC to guide therapeutic decisions.
Collapse
Affiliation(s)
- Philipp Jurmeister
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany.,Charité Comprehensive Cancer Center, 10117 Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), 69210 Heidelberg, Germany
| | - Michael Bockmayr
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany.,Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, 20251 Hamburg, Germany.,Research Institute Children's Cancer Center Hamburg, 20251 Hamburg, Germany
| | - Philipp Seegerer
- Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technical University of Berlin, 10623 Berlin, Germany
| | - Teresa Bockmayr
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany
| | - Denise Treue
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany
| | - Grégoire Montavon
- Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technical University of Berlin, 10623 Berlin, Germany
| | - Claudia Vollbrecht
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany.,German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), 69210 Heidelberg, Germany.,German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120 Heidelberg, Germany
| | - Alexander Arnold
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany
| | - Daniel Teichmann
- Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany
| | - Keno Bressem
- Department of Radiology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany
| | - Ulrich Schüller
- Department of Pediatric Hematology and Oncology, University Medical Center Hamburg-Eppendorf, 20251 Hamburg, Germany.,Research Institute Children's Cancer Center Hamburg, 20251 Hamburg, Germany.,Institute of Neuropathology, University Medical Center Hamburg-Eppendorf, 20251 Hamburg, Germany
| | - Maximilian von Laffert
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany
| | - Klaus-Robert Müller
- Machine-Learning Group, Department of Software Engineering and Theoretical Computer Science, Technical University of Berlin, 10623 Berlin, Germany.,Department of Brain and Cognitive Engineering, Korea University, 136-713 Seoul, South Korea.,Max-Planck-Institute for Informatics, 66123 Saarbrücken, Germany
| | - David Capper
- German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), 69210 Heidelberg, Germany. .,Department of Neuropathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany
| | - Frederick Klauschen
- Institute of Pathology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, 10117 Berlin, Germany. .,German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), 69210 Heidelberg, Germany
| |
Collapse
|
5
|
Hägele M, Seegerer P, Lapuschkin S, Bockmayr M, Samek W, Klauschen F, Müller KR, Binder A. Resolving challenges in deep learning-based analyses of histopathological images using explanation methods. Sci Rep 2020; 10:6423. [PMID: 32286358 PMCID: PMC7156509 DOI: 10.1038/s41598-020-62724-2] [Citation(s) in RCA: 60] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2019] [Accepted: 03/16/2020] [Indexed: 12/15/2022] Open
Abstract
Deep learning has recently gained popularity in digital pathology due to its high prediction quality. However, the medical domain requires explanation and insight for a better understanding beyond standard quantitative performance evaluation. Recently, many explanation methods have emerged. This work shows how heatmaps generated by these explanation methods allow to resolve common challenges encountered in deep learning-based digital histopathology analyses. We elaborate on biases which are typically inherent in histopathological image data. In the binary classification task of tumour tissue discrimination in publicly available haematoxylin-eosin-stained images of various tumour entities, we investigate three types of biases: (1) biases which affect the entire dataset, (2) biases which are by chance correlated with class labels and (3) sampling biases. While standard analyses focus on patch-level evaluation, we advocate pixel-wise heatmaps, which offer a more precise and versatile diagnostic instrument. This insight is shown to not only be helpful to detect but also to remove the effects of common hidden biases, which improves generalisation within and across datasets. For example, we could see a trend of improved area under the receiver operating characteristic (ROC) curve by 5% when reducing a labelling bias. Explanation techniques are thus demonstrated to be a helpful and highly relevant tool for the development and the deployment phases within the life cycle of real-world applications in digital pathology.
Collapse
Affiliation(s)
- Miriam Hägele
- TU Berlin, Machine Learning Group, Berlin, 10587, Germany
| | | | - Sebastian Lapuschkin
- Fraunhofer Heinrich Hertz Institute, Department of Video Coding & Analytics, Berlin, 10587, Germany
| | - Michael Bockmayr
- Charité University Hospital, Institute of Pathology, Berlin, 10117, Germany.,University Medical Center Hamburg-Eppendorf, Department of Pediatric Hematology and Oncology, Hamburg, 20251, Germany
| | - Wojciech Samek
- Fraunhofer Heinrich Hertz Institute, Department of Video Coding & Analytics, Berlin, 10587, Germany
| | - Frederick Klauschen
- Charité University Hospital, Institute of Pathology, Berlin, 10117, Germany.
| | - Klaus-Robert Müller
- TU Berlin, Machine Learning Group, Berlin, 10587, Germany. .,Korea University, Department of Brain and Cognitive Engineering, Anam-dong, Seongbuk-gu, Seoul, 02841, Korea. .,Max-Planck-Institute for Informatics, Campus E1 4, Saarbrücken, 66123, Germany.
| | - Alexander Binder
- Singapore University of Technology and Design, ISTD Pillar, Singapore, 487372, Singapore.
| |
Collapse
|
6
|
Klauschen F, Müller KR, Binder A, Bockmayr M, Hägele M, Seegerer P, Wienert S, Pruneri G, de Maria S, Badve S, Michiels S, Nielsen T, Adams S, Savas P, Symmans F, Willis S, Gruosso T, Park M, Haibe-Kains B, Gallas B, Thompson A, Cree I, Sotiriou C, Solinas C, Preusser M, Hewitt S, Rimm D, Viale G, Loi S, Loibl S, Salgado R, Denkert C. Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning. Semin Cancer Biol 2018; 52:151-157. [DOI: 10.1016/j.semcancer.2018.07.001] [Citation(s) in RCA: 61] [Impact Index Per Article: 10.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2018] [Revised: 07/01/2018] [Accepted: 07/02/2018] [Indexed: 12/12/2022]
|
7
|
Kayvanpour E, Mansi T, Sedaghat-Hamedani F, Amr A, Neumann D, Georgescu B, Seegerer P, Kamen A, Haas J, Frese KS, Irawati M, Wirsz E, King V, Buss S, Mereles D, Zitron E, Keller A, Katus HA, Comaniciu D, Meder B. Towards Personalized Cardiology: Multi-Scale Modeling of the Failing Heart. PLoS One 2015; 10:e0134869. [PMID: 26230546 PMCID: PMC4521877 DOI: 10.1371/journal.pone.0134869] [Citation(s) in RCA: 45] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2015] [Accepted: 07/14/2015] [Indexed: 01/14/2023] Open
Abstract
BACKGROUND Despite modern pharmacotherapy and advanced implantable cardiac devices, overall prognosis and quality of life of HF patients remain poor. This is in part due to insufficient patient stratification and lack of individualized therapy planning, resulting in less effective treatments and a significant number of non-responders. METHODS AND RESULTS State-of-the-art clinical phenotyping was acquired, including magnetic resonance imaging (MRI) and biomarker assessment. An individualized, multi-scale model of heart function covering cardiac anatomy, electrophysiology, biomechanics and hemodynamics was estimated using a robust framework. The model was computed on n=46 HF patients, showing for the first time that advanced multi-scale models can be fitted consistently on large cohorts. Novel multi-scale parameters derived from the model of all cases were analyzed and compared against clinical parameters, cardiac imaging, lab tests and survival scores to evaluate the explicative power of the model and its potential for better patient stratification. Model validation was pursued by comparing clinical parameters that were not used in the fitting process against model parameters. CONCLUSION This paper illustrates how advanced multi-scale models can complement cardiovascular imaging and how they could be applied in patient care. Based on obtained results, it becomes conceivable that, after thorough validation, such heart failure models could be applied for patient management and therapy planning in the future, as we illustrate in one patient of our cohort who received CRT-D implantation.
Collapse
Affiliation(s)
- Elham Kayvanpour
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany
| | - Tommaso Mansi
- Siemens Corporation, Corporate Technology, Imaging and Computer Vision, Princeton, New Jersey, United States of America
| | - Farbod Sedaghat-Hamedani
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany
| | - Ali Amr
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany
| | - Dominik Neumann
- Siemens Corporation, Corporate Technology, Imaging and Computer Vision, Princeton, New Jersey, United States of America
| | - Bogdan Georgescu
- Siemens Corporation, Corporate Technology, Imaging and Computer Vision, Princeton, New Jersey, United States of America
| | - Philipp Seegerer
- Siemens Corporation, Corporate Technology, Imaging and Computer Vision, Princeton, New Jersey, United States of America
| | - Ali Kamen
- Siemens Corporation, Corporate Technology, Imaging and Computer Vision, Princeton, New Jersey, United States of America
| | - Jan Haas
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany
| | - Karen S. Frese
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany
| | - Maria Irawati
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
| | - Emil Wirsz
- Siemens AG, Corporate Technology, Erlangen, Germany
| | - Vanessa King
- Siemens Corporation, Corporate Technology, Sensor Technologies, Princeton, New Jersey, United States of America
| | - Sebastian Buss
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
| | - Derliz Mereles
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
| | - Edgar Zitron
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
| | - Andreas Keller
- Biomarker Discovery Center Heidelberg, Heidelberg, Germany
- Department of Human Genetics, Saarland University, Homburg, Germany
| | - Hugo A. Katus
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany
- Klaus Tschira Institute for Computational Cardiology, Heidelberg, Germany
| | - Dorin Comaniciu
- Siemens Corporation, Corporate Technology, Imaging and Computer Vision, Princeton, New Jersey, United States of America
| | - Benjamin Meder
- Department of Medicine III, University of Heidelberg, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Heidelberg, Germany
- Klaus Tschira Institute for Computational Cardiology, Heidelberg, Germany
| |
Collapse
|
8
|
Seegerer P, Mansi T, Jolly MP, Neumann D, Georgescu B, Kamen A, Kayvanpour E, Amr A, Sedaghat-Hamedani F, Haas J, Katus H, Meder B, Comaniciu D. Estimation of Regional Electrical Properties of the Heart from 12-Lead ECG and Images. ACTA ACUST UNITED AC 2015. [DOI: 10.1007/978-3-319-14678-2_21] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/21/2023]
|
9
|
Zettinig O, Mansi T, Neumann D, Georgescu B, Rapaka S, Seegerer P, Kayvanpour E, Sedaghat-Hamedani F, Amr A, Haas J, Steen H, Katus H, Meder B, Navab N, Kamen A, Comaniciu D. Data-driven estimation of cardiac electrical diffusivity from 12-lead ECG signals. Med Image Anal 2014; 18:1361-76. [PMID: 24857832 DOI: 10.1016/j.media.2014.04.011] [Citation(s) in RCA: 30] [Impact Index Per Article: 3.0] [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: 01/07/2014] [Revised: 03/17/2014] [Accepted: 04/10/2014] [Indexed: 11/25/2022]
Abstract
Diagnosis and treatment of dilated cardiomyopathy (DCM) is challenging due to a large variety of causes and disease stages. Computational models of cardiac electrophysiology (EP) can be used to improve the assessment and prognosis of DCM, plan therapies and predict their outcome, but require personalization. In this work, we present a data-driven approach to estimate the electrical diffusivity parameter of an EP model from standard 12-lead electrocardiograms (ECG). An efficient forward model based on a mono-domain, phenomenological Lattice-Boltzmann model of cardiac EP, and a boundary element-based mapping of potentials to the body surface is employed. The electrical diffusivity of myocardium, left ventricle and right ventricle endocardium is then estimated using polynomial regression which takes as input the QRS duration and electrical axis. After validating the forward model, we computed 9500 EP simulations on 19 different DCM patients in just under three seconds each to learn the regression model. Using this database, we quantify the intrinsic uncertainty of electrical diffusion for given ECG features and show in a leave-one-patient-out cross-validation that the regression method is able to predict myocardium diffusion within the uncertainty range. Finally, our approach is tested on the 19 cases using their clinical ECG. 84% of them could be personalized using our method, yielding mean prediction errors of 18.7ms for the QRS duration and 6.5° for the electrical axis, both values being within clinical acceptability. By providing an estimate of diffusion parameters from readily available clinical data, our data-driven approach could therefore constitute a first calibration step toward a more complete personalization of cardiac EP.
Collapse
Affiliation(s)
- Oliver Zettinig
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA; Computer Aided Medical Procedures, Technische Universität München, Germany
| | - Tommaso Mansi
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA.
| | - Dominik Neumann
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA; Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
| | - Bogdan Georgescu
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA
| | - Saikiran Rapaka
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA
| | - Philipp Seegerer
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA; Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
| | | | | | - Ali Amr
- Heidelberg University Hospital, Heidelberg, Germany
| | - Jan Haas
- Heidelberg University Hospital, Heidelberg, Germany
| | | | - Hugo Katus
- Heidelberg University Hospital, Heidelberg, Germany
| | | | - Nassir Navab
- Computer Aided Medical Procedures, Technische Universität München, Germany
| | - Ali Kamen
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA
| | - Dorin Comaniciu
- Siemens Corporate Technology, Imaging and Computer Vision, Princeton, NJ, USA
| |
Collapse
|