Deep learning-based subtyping of gastric cancer histology predicts clinical outcome: a multi-institutional retrospective study

• Published in: Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association 2023-09, Vol.26 (5), p.708-720
• Main Authors: Veldhuizen, Gregory Patrick, Röcken, Christoph, Behrens, Hans-Michael, Cifci, Didem, Muti, Hannah Sophie, Yoshikawa, Takaki, Arai, Tomio, Oshima, Takashi, Tan, Patrick, Ebert, Matthias P., Pearson, Alexander T., Calderaro, Julien, Grabsch, Heike I., Kather, Jakob Nikolas
• Format: Article
• Language: English
• Subjects: Abdominal Surgery; Adenocarcinoma; Adenocarcinoma - pathology; Cancer Research; Classification; Clinical outcomes; Deep Learning; Diagnostics; Gastric cancer; Gastroenterology; Histology; Humans; Intestine; Machine learning; Medical prognosis; Medicine; Medicine & Public Health; Oncology; Original; Original Article; Pathophysiology; Prognosis; Proportional Hazards Models; Retrospective Studies; Stains & staining; Statistical analysis; Stomach Neoplasms - pathology; Surgical Oncology; Survival; Survival analysis; Typing
• ISSN: 1436-3291; 1436-3305; 1436-3305
• DOI: 10.1007/s10120-023-01398-x

Introduction The Laurén classification is widely used for Gastric Cancer (GC) histology subtyping. However, this classification is prone to interobserver variability and its prognostic value remains controversial. Deep Learning (DL)-based assessment of hematoxylin and eosin (H&E) stained slides is a potentially useful tool to provide an additional layer of clinically relevant information, but has not been systematically assessed in GC. Objective We aimed to train, test and externally validate a deep learning-based classifier for GC histology subtyping using routine H&E stained tissue sections from gastric adenocarcinomas and to assess its potential prognostic utility. Methods We trained a binary classifier on intestinal and diffuse type GC whole slide images for a subset of the TCGA cohort ( N  = 166) using attention-based multiple instance learning. The ground truth of 166 GC was obtained by two expert pathologists. We deployed the model on two external GC patient cohorts, one from Europe ( N  = 322) and one from Japan ( N  = 243). We assessed classification performance using the Area Under the Receiver Operating Characteristic Curve (AUROC) and prognostic value (overall, cancer specific and disease free survival) of the DL-based classifier with uni- and multivariate Cox proportional hazard models and Kaplan–Meier curves with log-rank test statistics. Results Internal validation using the TCGA GC cohort using five-fold cross-validation achieved a mean AUROC of 0.93 ± 0.07. External validation showed that the DL-based classifier can better stratify GC patients' 5-year survival compared to pathologist-based Laurén classification for all survival endpoints, despite frequently divergent model-pathologist classifications. Univariate overall survival Hazard Ratios (HRs) of pathologist-based Laurén classification (diffuse type versus intestinal type) were 1.14 (95% Confidence Interval (CI) 0.66–1.44, p -value = 0.51) and 1.23 (95% CI 0.96–1.43, p -value = 0.09) in the Japanese and European cohorts, respectively. DL-based histology classification resulted in HR of 1.46 (95% CI 1.18–1.65, p -value