Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes
Subtyping of non-small cell lung cancer (NSCLC) is paramount for therapy stratification. In this study, we analyzed the largest NSCLC cohort by mass spectrometry imaging (MSI) to date. We sought to test different classification algorithms and to validate results obtained in smaller patient cohorts....
Main Authors: | , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/12/9/2704 |
id |
doaj-b0f459c218eb493d9efff27619e17713 |
---|---|
record_format |
Article |
spelling |
doaj-b0f459c218eb493d9efff27619e177132020-11-25T01:46:22ZengMDPI AGCancers2072-66942020-09-01122704270410.3390/cancers12092704Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer SubtypesMark Kriegsmann0Christiane Zgorzelski1Rita Casadonte2Kristina Schwamborn3Thomas Muley4Hauke Winter5Martin Eichhorn6Florian Eichhorn7Arne Warth8Soeren-Oliver Deininger9Petros Christopoulos10Michael Thomas11Thomas Longerich12Albrecht Stenzinger13Wilko Weichert14Carsten Müller-Tidow15Jörg Kriegsmann16Peter Schirmacher17Katharina Kriegsmann18Institute of Pathology, University of Heidelberg, 69120 Heidelberg, GermanyInstitute of Pathology, University of Heidelberg, 69120 Heidelberg, GermanyProteopath Trier, 54296 Trier, GermanyInstitute of Pathology, TU Munich, 81675 Munich, GermanyTranslational Lung Research Centre Heidelberg, Member of the German Centre for Lung Research (DZL), 69120 Heidelberg, GermanyTranslational Lung Research Centre Heidelberg, Member of the German Centre for Lung Research (DZL), 69120 Heidelberg, GermanyTranslational Lung Research Centre Heidelberg, Member of the German Centre for Lung Research (DZL), 69120 Heidelberg, GermanyTranslational Lung Research Centre Heidelberg, Member of the German Centre for Lung Research (DZL), 69120 Heidelberg, GermanyInstitute of Pathology, Cytopathology, and Molecular Pathology, UEGP Gießen/Wetzlar/Limburg, 35578 Wetzlar, GermanyBruker Daltonik, 28359 Bremen, GermanyTranslational Lung Research Centre Heidelberg, Member of the German Centre for Lung Research (DZL), 69120 Heidelberg, GermanyTranslational Lung Research Centre Heidelberg, Member of the German Centre for Lung Research (DZL), 69120 Heidelberg, GermanyInstitute of Pathology, University of Heidelberg, 69120 Heidelberg, GermanyInstitute of Pathology, University of Heidelberg, 69120 Heidelberg, GermanyInstitute of Pathology, TU Munich, 81675 Munich, GermanyDepartment of Hematology, Oncology and Rheumatology, University of Heidelberg, 69120 Heidelberg, GermanyProteopath Trier, 54296 Trier, GermanyInstitute of Pathology, University of Heidelberg, 69120 Heidelberg, GermanyDepartment of Hematology, Oncology and Rheumatology, University of Heidelberg, 69120 Heidelberg, GermanySubtyping of non-small cell lung cancer (NSCLC) is paramount for therapy stratification. In this study, we analyzed the largest NSCLC cohort by mass spectrometry imaging (MSI) to date. We sought to test different classification algorithms and to validate results obtained in smaller patient cohorts. Tissue microarrays (TMAs) from including adenocarcinoma (ADC, <i>n</i> = 499) and squamous cell carcinoma (SqCC, <i>n</i> = 440), were analyzed. Linear discriminant analysis, support vector machine, and random forest (RF) were applied using samples randomly assigned for training (66%) and validation (33%). The <i>m/z</i> species most relevant for the classification were identified by on-tissue tandem mass spectrometry and validated by immunohistochemistry (IHC). Measurements from multiple TMAs were comparable using standardized protocols. RF yielded the best classification results. The classification accuracy decreased after including less than six of the most relevant <i>m/z</i> species. The sensitivity and specificity of MSI in the validation cohort were 92.9% and 89.3%, comparable to IHC. The most important protein for the discrimination of both tumors was cytokeratin 5. We investigated the largest NSCLC cohort by MSI to date and found that the classification of NSCLC into ADC and SqCC is possible with high accuracy using a limited set of <i>m/z</i> species.https://www.mdpi.com/2072-6694/12/9/2704mass spectrometry imagingmass spectrometryNSCLClung cancer |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mark Kriegsmann Christiane Zgorzelski Rita Casadonte Kristina Schwamborn Thomas Muley Hauke Winter Martin Eichhorn Florian Eichhorn Arne Warth Soeren-Oliver Deininger Petros Christopoulos Michael Thomas Thomas Longerich Albrecht Stenzinger Wilko Weichert Carsten Müller-Tidow Jörg Kriegsmann Peter Schirmacher Katharina Kriegsmann |
spellingShingle |
Mark Kriegsmann Christiane Zgorzelski Rita Casadonte Kristina Schwamborn Thomas Muley Hauke Winter Martin Eichhorn Florian Eichhorn Arne Warth Soeren-Oliver Deininger Petros Christopoulos Michael Thomas Thomas Longerich Albrecht Stenzinger Wilko Weichert Carsten Müller-Tidow Jörg Kriegsmann Peter Schirmacher Katharina Kriegsmann Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes Cancers mass spectrometry imaging mass spectrometry NSCLC lung cancer |
author_facet |
Mark Kriegsmann Christiane Zgorzelski Rita Casadonte Kristina Schwamborn Thomas Muley Hauke Winter Martin Eichhorn Florian Eichhorn Arne Warth Soeren-Oliver Deininger Petros Christopoulos Michael Thomas Thomas Longerich Albrecht Stenzinger Wilko Weichert Carsten Müller-Tidow Jörg Kriegsmann Peter Schirmacher Katharina Kriegsmann |
author_sort |
Mark Kriegsmann |
title |
Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes |
title_short |
Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes |
title_full |
Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes |
title_fullStr |
Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes |
title_full_unstemmed |
Mass Spectrometry Imaging for Reliable and Fast Classification of Non-Small Cell Lung Cancer Subtypes |
title_sort |
mass spectrometry imaging for reliable and fast classification of non-small cell lung cancer subtypes |
publisher |
MDPI AG |
series |
Cancers |
issn |
2072-6694 |
publishDate |
2020-09-01 |
description |
Subtyping of non-small cell lung cancer (NSCLC) is paramount for therapy stratification. In this study, we analyzed the largest NSCLC cohort by mass spectrometry imaging (MSI) to date. We sought to test different classification algorithms and to validate results obtained in smaller patient cohorts. Tissue microarrays (TMAs) from including adenocarcinoma (ADC, <i>n</i> = 499) and squamous cell carcinoma (SqCC, <i>n</i> = 440), were analyzed. Linear discriminant analysis, support vector machine, and random forest (RF) were applied using samples randomly assigned for training (66%) and validation (33%). The <i>m/z</i> species most relevant for the classification were identified by on-tissue tandem mass spectrometry and validated by immunohistochemistry (IHC). Measurements from multiple TMAs were comparable using standardized protocols. RF yielded the best classification results. The classification accuracy decreased after including less than six of the most relevant <i>m/z</i> species. The sensitivity and specificity of MSI in the validation cohort were 92.9% and 89.3%, comparable to IHC. The most important protein for the discrimination of both tumors was cytokeratin 5. We investigated the largest NSCLC cohort by MSI to date and found that the classification of NSCLC into ADC and SqCC is possible with high accuracy using a limited set of <i>m/z</i> species. |
topic |
mass spectrometry imaging mass spectrometry NSCLC lung cancer |
url |
https://www.mdpi.com/2072-6694/12/9/2704 |
work_keys_str_mv |
AT markkriegsmann massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT christianezgorzelski massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT ritacasadonte massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT kristinaschwamborn massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT thomasmuley massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT haukewinter massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT martineichhorn massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT florianeichhorn massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT arnewarth massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT soerenoliverdeininger massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT petroschristopoulos massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT michaelthomas massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT thomaslongerich massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT albrechtstenzinger massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT wilkoweichert massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT carstenmullertidow massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT jorgkriegsmann massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT peterschirmacher massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes AT katharinakriegsmann massspectrometryimagingforreliableandfastclassificationofnonsmallcelllungcancersubtypes |
_version_ |
1725019835690123264 |