Related Experiment Video
Updated: Jun 3, 2026
05:33
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
From Bench to Bedside: The Path Toward Real-World Translation for Artificial Intelligence in Pancreatic Cancer
Emir A Syailendra1, Hajra Arshad1, Felipe Lopez-Ramirez1
1Russell H. Morgan Department of Radiology and Radiological Science, School of Medicine, Johns Hopkins University, Baltimore, MD, USA.
Korean Journal of Radiology
|June 1, 2026
Summary
Artificial intelligence (AI) shows promise for early pancreatic cancer detection by identifying subtle imaging changes. However, challenges in reproducibility, generalizability, and clinical integration hinder its real-world application.
Area of Science:
- Oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Pancreatic cancer has low survival rates due to late-stage diagnosis.
- Current early detection methods (imaging, blood tests, genetic sequencing) have limited accuracy.
- Artificial intelligence (AI) models can detect subtle pre-diagnostic imaging anomalies.
Purpose of the Study:
- To review the current state of AI in pancreatic cancer detection.
- To outline barriers to the clinical translation of AI for pancreatic cancer detection.
Main Methods:
- Review of current AI models for pancreatic cancer detection.
- Analysis of challenges in AI implementation and clinical translation.
Main Results:
- AI models show potential for earlier and more consistent pancreatic cancer detection.
- Significant barriers exist, including issues with model reproducibility and generalizability across institutions.
- Lack of prospective validation and practical implementation challenges (workflow, cost, monitoring) impede clinical use.
Conclusions:
- AI holds promise for improving pancreatic cancer early detection.
- Overcoming barriers related to AI model performance, validation, and practical integration is crucial for clinical adoption.
- Addressing non-model-specific challenges is essential for successful translation of AI into clinical practice.
