TY - JOUR
AU - Bitto, Verena
AU - Jiang, Xiaofeng
AU - Baumann, Michael
AU - Kather, Jakob Nikolas
AU - Kurth, Ina
TI - Deep Learning Predicts Survival Across Squamous Tumor Entities From Routine Pathology: Insights from Head and Neck, Esophagus, Lung and Cervical Cancer.
JO - Modern pathology
VL - 38
IS - 12
SN - 0893-3952
CY - London
PB - Nature Publishing Group
M1 - DKFZ-2025-01454
SP - 100845
PY - 2025
N1 - #EA:E220#LA:E220# / Volume 38, Issue 12, December 2025, 100845
AB - Computational pathology-based models are becoming increasingly popular for extracting biomarkers from images of cancer tissue. However, their validity is often only demonstrated on a single unseen validation cohort, limiting insights into their generalizability and posing challenges for explainability. In this study, we developed models to predict overall survival using haematoxylin and eosin (H</td><td width="150">
AB - E) slides from formalin-fixed paraffin-embedded (FFPE) samples in head and neck squamous cell carcinoma (HNSCC). By validating our models across diverse squamous tumor entities, including head and neck (hazard ratio [HR] = 1.58, 95
KW - computational pathology (Other)
KW - feature extraction (Other)
KW - histopathology (Other)
KW - squamous cell carcinomas (Other)
KW - survival models (Other)
LB - PUB:(DE-HGF)16
C6 - pmid:40680853
DO - DOI:10.1016/j.modpat.2025.100845
UR - https://inrepo02.dkfz.de/record/303007
ER -