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

Autor:	Carretero-Barrio I; Department of Pathology, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS), 28034, Madrid, Spain.; Faculty of Medicine, Universidad de Alcalá, 28801, Alcalá de Henares, Spain.; CIBERONC, 28029, Madrid, Spain., Pijuan L; Department of Pathology, Hospital Universitari Bellvitge, L'Hospitalet de Llobregat, 08097, Barcelona, Spain., Illarramendi A; Department of Pathology, Hospital Universitario 12 de Octubre, 28041, Madrid, Spain., Curto D; Department of Pathology, Hospital Universitario 12 de Octubre, 28041, Madrid, Spain., López-Ríos F; CIBERONC, 28029, Madrid, Spain.; Department of Pathology, Hospital Universitario 12 de Octubre, 28041, Madrid, Spain., Estébanez-Gallo Á; Department of Pathology, Hospital Universitario Marqués de Valdecilla, 39011, Santander, Spain., Castellvi J; CIBERONC, 28029, Madrid, Spain.; Department of Pathology, Hospital Universitario Vall D'Hebron, 08035, Barcelona, Spain., Granados-Aparici S; CIBERONC, 28029, Madrid, Spain.; Department of Pathology, Medical School, University of Valencia-INCLIVA, 46010, Valencia, Spain., Compañ-Quilis D; Department of Pathology, Hospital Clínico Universitario de Valencia, 46010, Valencia, Spain., Noguera R; CIBERONC, 28029, Madrid, Spain.; Department of Pathology, Medical School, University of Valencia-INCLIVA, 46010, Valencia, Spain., Esteban-Rodríguez I; Department of Pathology, Hospital Universitario La Paz, 28046, Madrid, Spain., Sánchez-Güerri I; Department of Pathology, Hospital del Mar, 08003, Barcelona, Spain., Ramos-Guerra AD; CIBER-BBN, ISCIII, 28029, Madrid, Spain.; Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid, 28040, Madrid, Spain., Ortuño JE; CIBER-BBN, ISCIII, 28029, Madrid, Spain.; Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid, 28040, Madrid, Spain., Garrido P; Faculty of Medicine, Universidad de Alcalá, 28801, Alcalá de Henares, Spain.; CIBERONC, 28029, Madrid, Spain.; Medical Oncology Department, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS), 28034, Madrid, Spain., Ledesma-Carbayo MJ; CIBER-BBN, ISCIII, 28029, Madrid, Spain.; Biomedical Image Technologies, ETSI Telecomunicación, Universidad Politécnica de Madrid, 28040, Madrid, Spain., Benito A; Department of Pathology, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS), 28034, Madrid, Spain.; Faculty of Medicine, Universidad de Alcalá, 28801, Alcalá de Henares, Spain., Palacios J; Department of Pathology, Hospital Universitario Ramón y Cajal, Instituto Ramón y Cajal de Investigación Sanitaria (IRYCIS), 28034, Madrid, Spain. jose.palacios@salud.madrid.org.; Faculty of Medicine, Universidad de Alcalá, 28801, Alcalá de Henares, Spain. jose.palacios@salud.madrid.org.; CIBERONC, 28029, Madrid, Spain. jose.palacios@salud.madrid.org.
Jazyk:	angličtina
Zdroj:	Scientific reports [Sci Rep] 2024 Oct 15; Vol. 14 (1), pp. 24163. Date of Electronic Publication: 2024 Oct 15.
DOI:	10.1038/s41598-024-75175-w
Abstrakt:	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. (© 2024. The Author(s).)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu Plný text ve formátu PDF