Automated interpretation of PD-L1 CPS based on multi-AI models integration strategy in gastric cancer
Open Access
- 6 August 2025
- journal article
- immunology
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 16, 1614099
Abstract
Introduction: Programmed cell death ligand-1 (PD-L1) combined positive score (CPS) evaluation plays a pivotal role in predicting immunotherapy efficacy for gastric cancer. However, manual CPS assessment suffers from significant inter-observer variability among pathologists, leading to clinical inconsistencies. To address this limitation, we developed a deep learning-based artificial intelligence (AI) system that automates PD-L1 CPS quantification for patients with gastric cancer (GC) using whole slide images (WSIs).Methods: We developed a deep learning-based artificial intelligence (AI) system that automates PD-L1 CPS quantification for patients with gastric cancer (GC) using whole slide images (WSIs). Our pipeline firstly employs a dual-network architecture for tumor region detection: MobileNet for patch-level classification and U-Net for pixel-level segmentation. Followed by a YOLO-based cell detection model to compute PD-L1 expression on different cells for CPS calculation. A total of 308 GC WSIs were included, including 210 in the internal cohort and 98 in the external cohort. Within the internal cohort, 100 WSIs were utilized for the model development, while the remaining 110 WSIs served as an internal testing set for comparative analysis between AI-derived CPS values and pathologist-derived reference standards.Results: The AI-derived CPS demonstrated strong concordance with expert pathologists’ consensus in internal cohort (Cohen’s kappa = 0.782). Furthermore, the AI-based CPS prediction pipeline was evaluated for its performance in the external cohort, and showed robust performance (Cohen’s kappa = 0.737).Discussion: Our system provides a standardized decision-support tool for immunotherapy stratification in GC management, demonstrating potential to improve CPS assessment reproducibility.Keywords
This publication has 30 references indexed in Scilit:
- Segment anything in medical imagesNature Communications, 2024
- Global, regional, and national lifetime risks of developing and dying from gastrointestinal cancers in 185 countries: a population-based systematic analysis of GLOBOCANThe Lancet Gastroenterology & Hepatology, 2024
- Sintilimab Plus Chemotherapy for Unresectable Gastric or Gastroesophageal Junction CancerJAMA, 2023
- High Interobserver Variability Among Pathologists Using Combined Positive Score to Evaluate PD-L1 Expression in Gastric, Gastroesophageal Junction, and Esophageal AdenocarcinomaLaboratory Investigation, 2023
- The Role of Artificial Intelligence in Accurate Interpretation of HER2 Immunohistochemical Scores 0 and 1+ in Breast CancerLaboratory Investigation, 2023
- GasHis-Transformer: A multi-scale visual transformer approach for gastric histopathological image detectionPattern Recognition, 2022
- Artificial intelligence-assisted system for precision diagnosis of PD-L1 expression in non-small cell lung cancerLaboratory Investigation, 2022
- Deep learning in cancer pathology: a new generation of clinical biomarkersBritish Journal of Cancer, 2020
- Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast CancerJAMA, 2017
- PD-L1 Immunohistochemistry Assays for Lung Cancer: Results from Phase 1 of the Blueprint PD-L1 IHC Assay Comparison ProjectJournal of Thoracic Oncology, 2017