PuSH - Publikationsserver des Helmholtz Zentrums München

Gindra, R. ; Zheng, Y.* ; Green, E.J.* ; Reid, M.E.* ; Mazzilli, S.A.* ; Merrick, D.T.* ; Burks, E.J.* ; Kolachalama, V.B.* ; Beane, J.E.*

Graph perceiver network for lung tumor and bronchial premalignant lesion stratification from histopathology.

Am. J. Pathol. 194, 1285-1293 (2024)
DOI PMC
Open Access Green: Postprint online verfügbar 05/2025
Bronchial premalignant lesions (PMLs) precede the development of invasive lung squamous carcinoma (LUSC), posing a significant challenge in distinguishing those likely to advance to LUSC from those that might regress without intervention. In this context, we present a novel computational approach, the Graph Perceiver Network (GRAPE-Net), leveraging hematoxylin and eosin (H&E) stained whole slide images (WSIs) to stratify endobronchial biopsies of PMLs across a spectrum from normal to tumor lung tissues. GRAPE-Net outperforms existing frameworks in classification accuracy predicting LUSC, lung adenocarcinoma (LUAD), and non-tumor (normal) lung tissue on The Cancer Genome Atlas (TCGA) and Clinical Proteomic Tumor Analysis Consortium (CPTAC) datasets containing lung resection tissues while efficiently generating pathologist-aligned, class-specific heatmaps. The network was further tested using endobronchial biopsies from two data cohorts, containing normal to carcinoma in situ histology, and it demonstrated a unique capability to differentiate carcinoma in situ lung squamous PMLs based on their progression status to invasive carcinoma. The network may have utility in stratifying PMLs for chemoprevention trials or more aggressive follow-up.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
Schlagwörter Lung Cancer ; Deep Learning ; Digital Pathology ; Premalignant Lesions
ISSN (print) / ISBN 0002-9440
e-ISSN 1525-2191
Zeitschrift American Journal of Pathology, The
Quellenangaben Band: 194, Heft: 7, Seiten: 1285-1293 Artikelnummer: , Supplement: ,
Verlag Elsevier
Verlagsort Ste 800, 230 Park Ave, New York, Ny 10169 Usa
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Förderungen Karen Toffler Charitable Trust
Johnson &Johnson Enterprise Innovation, Inc.
American Heart Association
NIH