Related Experiment Video
Updated: Sep 18, 2025
08:30
Immunophenotyping of Orthotopic Homograft Syngeneic of Murine Primary KPC Pancreatic Ductal Adenocarcinoma by Flow Cytometry
Published on: October 9, 2018
12.5K
Artificial Intelligence-Powered Spatial Analysis of Immune Phenotypes in Resected Pancreatic Cancer
Hyemin Kim1, Jin Ho Choi1,2, Yoojoo Lim3
1Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
JAMA Surgery
|June 25, 2025
Summary
Artificial intelligence (AI) spatial analysis of tumor-infiltrating lymphocytes (TILs) in pancreatic cancer improves prognostic assessment. This AI approach simplifies TIL evaluation, making it more practical for clinical use and identifying immune phenotypes as key biomarkers.
Area of Science:
- Oncology
- Immunology
- Artificial Intelligence in Medicine
Background:
- Tumor-infiltrating lymphocytes (TILs) are crucial prognostic biomarkers in various cancers.
- Clinical application of TILs is hindered by challenges in assessment and interpretation.
- Pancreatic ductal adenocarcinoma (PDAC) requires improved prognostic tools for patient management.
Purpose of the Study:
- To evaluate the prognostic significance of AI-powered spatial TIL analysis in resected PDAC.
- To assess the clinical applicability of AI for TIL density and immune phenotype classification.
- To identify tumor microenvironment factors associated with overall survival (OS) and recurrence-free survival (RFS).
Main Methods:
- A cohort study of 304 patients with resected PDAC (R0) was conducted.
- Whole-slide images were analyzed using an AI-powered system for TIL quantification and spatial mapping.
- Tumor immune phenotypes (immune-inflamed, immune-excluded, immune-desert) were classified.
Main Results:
- The immune-inflamed phenotype was associated with significantly longer OS and RFS (P < .001).
- High intratumoral TIL density correlated with improved OS (median 52.47 months) and RFS (median 21.67 months).
- AI analysis condensed the labor-intensive TIL assessment process, enhancing clinical feasibility.
Conclusions:
- AI-powered spatial TIL analysis offers a practical and feasible method for prognostic assessment in resected PDAC.
- Immune phenotype, particularly the immune-inflamed type, is a significant prognostic biomarker in PDAC.
- This AI approach has the potential to refine patient stratification and guide treatment decisions.
