Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology

Abstract The incorporation of digital pathology in clinical practice will require the training of pathologists in digital skills. Our study aimed to assess the reliability among pathologists in determining tumor percentage in whole slide images (WSI) of non-small cell lung cancer (NSCLC) using digit...

Full description

Saved in:
Bibliographic Details
Main Authors: Irene Carretero-Barrio, Lara Pijuan, Adrián Illarramendi, Daniel Curto, Fernando López-Ríos, Ángel Estébanez-Gallo, Josep Castellvi, Sofía Granados-Aparici, Desamparados Compañ-Quilis, Rosa Noguera, Isabel Esteban-Rodríguez, Ignacio Sánchez-Güerri, Ana Delia Ramos-Guerra, Juan Enrique Ortuño, Pilar Garrido, María Jesús Ledesma-Carbayo, Amparo Benito, José Palacios
Format: Article
Language:English
Published: Nature Portfolio 2024-10-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-75175-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850182088215494656
author Irene Carretero-Barrio
Lara Pijuan
Adrián Illarramendi
Daniel Curto
Fernando López-Ríos
Ángel Estébanez-Gallo
Josep Castellvi
Sofía Granados-Aparici
Desamparados Compañ-Quilis
Rosa Noguera
Isabel Esteban-Rodríguez
Ignacio Sánchez-Güerri
Ana Delia Ramos-Guerra
Juan Enrique Ortuño
Pilar Garrido
María Jesús Ledesma-Carbayo
Amparo Benito
José Palacios
author_facet Irene Carretero-Barrio
Lara Pijuan
Adrián Illarramendi
Daniel Curto
Fernando López-Ríos
Ángel Estébanez-Gallo
Josep Castellvi
Sofía Granados-Aparici
Desamparados Compañ-Quilis
Rosa Noguera
Isabel Esteban-Rodríguez
Ignacio Sánchez-Güerri
Ana Delia Ramos-Guerra
Juan Enrique Ortuño
Pilar Garrido
María Jesús Ledesma-Carbayo
Amparo Benito
José Palacios
author_sort Irene Carretero-Barrio
collection DOAJ
description Abstract The incorporation of digital pathology in clinical practice will require the training of pathologists in digital skills. Our study aimed to assess the reliability among pathologists in determining tumor percentage in whole slide images (WSI) of non-small cell lung cancer (NSCLC) using digital image analysis, and study how the results correlate with the molecular findings. Pathologists from nine centers were trained to quantify epithelial tumor cells, tumor-associated stromal cells, and non-neoplastic cells from NSCLC WSI using QuPath. Then, we conducted two consecutive ring trials. In the first trial, analyzing four WSI, reliability between pathologists in the assessment of tumor cell percentage was poor (intraclass correlation coefficient (ICC) 0.09). After performing the first ring trial pathologists received feedback. The second trial, comprising 10 WSI with paired next-generation sequencing results, also showed poor reliability (ICC 0.24). Cases near the recommended 20% visual threshold for molecular techniques exhibited higher values with digital analysis. In the second ring trial reliability slightly improved and human errors were reduced from 5.6% to 1.25%. Most discrepancies arose from subjective tasks, such as the annotation process, suggesting potential improvement with future artificial intelligence solutions.
format Article
id doaj-art-a9844491cfaf44f3a06678590667aee4
institution OA Journals
issn 2045-2322
language English
publishDate 2024-10-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-a9844491cfaf44f3a06678590667aee42025-08-20T02:17:45ZengNature PortfolioScientific Reports2045-23222024-10-0114111110.1038/s41598-024-75175-wConcordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathologyIrene Carretero-Barrio0Lara Pijuan1Adrián Illarramendi2Daniel Curto3Fernando López-Ríos4Ángel Estébanez-Gallo5Josep Castellvi6Sofía Granados-Aparici7Desamparados Compañ-Quilis8Rosa Noguera9Isabel Esteban-Rodríguez10Ignacio Sánchez-Güerri11Ana Delia Ramos-Guerra12Juan Enrique Ortuño13Pilar Garrido14María Jesús Ledesma-Carbayo15Amparo Benito16José Palacios17Department of Pathology, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS)Department of Pathology, Hospital Universitari BellvitgeDepartment of Pathology, Hospital Universitario 12 de OctubreDepartment of Pathology, Hospital Universitario 12 de OctubreCIBERONCDepartment of Pathology, Hospital Universitario Marqués de ValdecillaCIBERONCCIBERONCDepartment of Pathology, Hospital Clínico Universitario de ValenciaCIBERONCDepartment of Pathology, Hospital Universitario La PazDepartment of Pathology, Hospital del MarCIBER-BBN, ISCIIICIBER-BBN, ISCIIIFaculty of Medicine, Universidad de AlcaláCIBER-BBN, ISCIIIDepartment of Pathology, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS)Department of Pathology, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS)Abstract The incorporation of digital pathology in clinical practice will require the training of pathologists in digital skills. Our study aimed to assess the reliability among pathologists in determining tumor percentage in whole slide images (WSI) of non-small cell lung cancer (NSCLC) using digital image analysis, and study how the results correlate with the molecular findings. Pathologists from nine centers were trained to quantify epithelial tumor cells, tumor-associated stromal cells, and non-neoplastic cells from NSCLC WSI using QuPath. Then, we conducted two consecutive ring trials. In the first trial, analyzing four WSI, reliability between pathologists in the assessment of tumor cell percentage was poor (intraclass correlation coefficient (ICC) 0.09). After performing the first ring trial pathologists received feedback. The second trial, comprising 10 WSI with paired next-generation sequencing results, also showed poor reliability (ICC 0.24). Cases near the recommended 20% visual threshold for molecular techniques exhibited higher values with digital analysis. In the second ring trial reliability slightly improved and human errors were reduced from 5.6% to 1.25%. Most discrepancies arose from subjective tasks, such as the annotation process, suggesting potential improvement with future artificial intelligence solutions.https://doi.org/10.1038/s41598-024-75175-w
spellingShingle Irene Carretero-Barrio
Lara Pijuan
Adrián Illarramendi
Daniel Curto
Fernando López-Ríos
Ángel Estébanez-Gallo
Josep Castellvi
Sofía Granados-Aparici
Desamparados Compañ-Quilis
Rosa Noguera
Isabel Esteban-Rodríguez
Ignacio Sánchez-Güerri
Ana Delia Ramos-Guerra
Juan Enrique Ortuño
Pilar Garrido
María Jesús Ledesma-Carbayo
Amparo Benito
José Palacios
Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology
Scientific Reports
title Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology
title_full Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology
title_fullStr Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology
title_full_unstemmed Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology
title_short Concordance in the estimation of tumor percentage in non-small cell lung cancer using digital pathology
title_sort concordance in the estimation of tumor percentage in non small cell lung cancer using digital pathology
url https://doi.org/10.1038/s41598-024-75175-w
work_keys_str_mv AT irenecarreterobarrio concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT larapijuan concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT adrianillarramendi concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT danielcurto concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT fernandolopezrios concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT angelestebanezgallo concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT josepcastellvi concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT sofiagranadosaparici concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT desamparadoscompanquilis concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT rosanoguera concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT isabelestebanrodriguez concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT ignaciosanchezguerri concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT anadeliaramosguerra concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT juanenriqueortuno concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT pilargarrido concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT mariajesusledesmacarbayo concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT amparobenito concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology
AT josepalacios concordanceintheestimationoftumorpercentageinnonsmallcelllungcancerusingdigitalpathology