gms | German Medical Science

73. Jahrestagung der Deutschen Gesellschaft für Neurochirurgie (DGNC)
Joint Meeting mit der Griechischen Gesellschaft für Neurochirurgie

Deutsche Gesellschaft für Neurochirurgie (DGNC) e. V.

29.05. - 01.06.2022, Köln

Article

Send article

Radiomics for the non-invasive assessment of the PDL-1 expression in patients with non-small cell lung cancer brain metastases

Radiomics zur nicht-invasiven Bestimmung der PDL-1 Expression bei Patienten mit Hirnmetastasen bei nicht-kleinzelligem Lungenkrebs

Meeting Abstract

Search Medline for

  • presenting/speaker Anna-Katharina Meißner - Universitätsklinikum Köln, Department of General Neurosurgery, Köln, Deutschland
  • Robin Gutsche - Research Centre Jülich, Institute of Neuroscience and Medicine, Jülich, Deutschland
  • Norbert Galldiks - Research Centre Jülich, Institute of Neuroscience and Medicine, Jülich, Deutschland; Universitätsklinikum Köln, Department of Neurology, Köln, Deutschland; Universities of Aachen, Bonn, Cologne and Duesseldorf, Center for Integrated Oncology (CIO), Köln, Deutschland
  • Martin Kocher - Universitätsklinikum Köln, Department of Stereotactic and Functional Neurosurgery, Köln, Deutschland; Research Centre Jülich, Institute of Neuroscience and Medicine, Jülich, Deutschland
  • Stephanie T. Jünger - Universitätsklinikum Köln, Department of General Neurosurgery, Köln, Deutschland
  • Marie-Lisa Eich - Universitätsklinikum Köln, Department of Pathology, Köln, Deutschland
  • Lucia Nogova - Universitätsklinikum Köln, Department I of Internal Medicine, Köln, Deutschland
  • Nils-Ole Schmidt - Universitätsklinikum Regensburg, Klinik und Poliklinik für Neurochirurgie, Regensburg, Deutschland
  • Maximilian I. Ruge - Universitätsklinikum Köln, Department of Stereotactic and Functional Neurosurgery, Köln, Deutschland; Universities of Aachen, Bonn, Cologne and Duesseldorf, Center for Integrated Oncology (CIO), Köln, Deutschland
  • Roland Goldbrunner - Universitätsklinikum Köln, Department of General Neurosurgery, Köln, Deutschland; Universities of Aachen, Bonn, Cologne and Duesseldorf, Center for Integrated Oncology (CIO), Köln, Deutschland
  • Martin Proescholdt - Universitätsklinikum Regensburg, Klinik und Poliklinik für Neurochirurgie, Regensburg, Deutschland
  • Stefan Grau - Klinikum Fulda, Universitätsmedizin Marburg, Klinik für Neurochirurgie, Fulda, Deutschland
  • Philipp Lohmann - Universitätsklinikum Köln, Department of Stereotactic and Functional Neurosurgery, Köln, Deutschland; Research Centre Jülich, Institute of Neuroscience and Medicine, Jülich, Deutschland

Deutsche Gesellschaft für Neurochirurgie. 73. Jahrestagung der Deutschen Gesellschaft für Neurochirurgie (DGNC), Joint Meeting mit der Griechischen Gesellschaft für Neurochirurgie. Köln, 29.05.-01.06.2022. Düsseldorf: German Medical Science GMS Publishing House; 2022. DocV300

doi: 10.3205/22dgnc290, urn:nbn:de:0183-22dgnc2908

Published: May 25, 2022

© 2022 Meißner et al.
This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 License. See license information at http://creativecommons.org/licenses/by/4.0/.

Outline

Text

Objective: The expression level of programmed cell death ligand 1 (PDL-1) might be an indicator for response to immunotherapy using checkpoint inhibitors in patients with non-small cell lung cancer (NSCLC). As intra-tumoral differences and discrepancies between the PDL-1 expression in the primary tumor and the brain metastases may occur, a method for a reliable non-invasive assessment of the intracranial PDL-1 expression would be of clinical value. We evaluated the potential of MRI radiomics for a non-invasive assessment of the PD-L1 expression in patients with NSCLC brain metastases.

Methods: Thirty-six patients with brain metastases from NSCLC underwent brain tumor resection with subsequent immunohistochemical assessment of the PDL-1 expression. Brain metastases were manually segmented on preoperative contrast-enhanced MRI. After radiomics feature extraction from T1-weighted contrast-enhanced and T2-weighted MRI, a test-retest analysis was performed to identify robust features prior to feature selection. The radiomics model was trained and validated using five-fold cross validation. Diagnostic performance was evaluated using receiver operating characteristic (ROC) analyses.

Results: An intracranial PDL-1 expression was found by immunohistochemistry in 18 of 36 patients (50%). Univariate analysis identified tumor volume as a significant clinical feature for PDL-1 expression (area under the ROC curve (AUC), 0.77). A random forest classifier using a six-parameter radiomics signature yielded an AUC of 0.88 ± 0.07. The combination of the radiomics features with tumor volume did not further increase the model performance.

Conclusion: The developed radiomics classifiers allows a non-invasive assessment of the intracranial PD-L1 expression in patients with NSCLC brain metastases with a high diagnostic performance. Further evaluation of the developed radiomics model in an external test dataset is ongoing.