TITLE:
The Role of Artificial Intelligence in Pancreatic Cancer Detection: A Systematic Review
AUTHORS:
Jahnavi Ethakota, Bipneet Singh, Sakshi Bai, Haseeb Tareen, Danesh Kumar, Devin Birsingh Malik
KEYWORDS:
Pancreatic Cancer, Artificial Intelligence, Detection, Endoscopic Ultrasound, Pet Scan, CT Scan
JOURNAL NAME:
Open Journal of Gastroenterology,
Vol.15 No.4,
April
18,
2025
ABSTRACT: Background: Pancreatic cancer is the fourth leading cause of cancer deaths in the United States, and early detection remains a significant challenge. Screening the general population is not feasible, but the rise of artificial intelligence (AI) has introduced new possibilities for improving early diagnosis and patient outcomes. Methods: A systematic literature search was conducted using PubMed, Google Scholar, and MEDLINE using MeSH terms “Artificial intelligence or AI”, and “diagnosis” and “pancreatic carcinoma or pancreatic adenocarcinoma”. Prisma guidelines were adhered to, and a total of 47 studies resulted, 10 articles were duplicates, 11 articles were excluded as they did not align with the topic, 7 articles could not be retrieved, 13 articles were excluded as they did not fit the criteria, 6 retrospective studies are included in this study. The inclusion criteria for this study are AI being used in the diagnosis, only in pancreatic cancer, within the last 5 years, only in English, and only retrospective studies were included. Results: One study used Digital Imaging Processing (DIP) for analyzing Endoscopic ultrasound (EUS) images from 153 pancreatic cancer patients, yielding a sensitivity of 97.98% and a specificity of 94.32%. Two studies explored Computer Aided Diagnosis (CAD) models applied to PET/CT and EUS images, achieving a sensitivity of 95.23% and specificity of 97.51% in PET/CT scans and 83.3% and 93.3% in EUS images, respectively. Another study used a Faster R-CNN model to analyze CT images from 338 pancreatic cancer patients showed high diagnostic accuracy in much less time. Additionally, two studies utilized Natural Language Processing (NLP) for identifying family histories of pancreatic cancer and detecting pancreatic cysts, with the latter achieving sensitivity and specificity rates of 99.9% and 98.8%. Conclusions: The current strategies for early diagnosis of pancreatic cancer focus on serum biomarkers and EUS-guided Fine Needle Aspiration (EUS-FNA). Sensitivity varies and depends on the physician’s expertise. AI is showing promise in improving pancreatic cancer diagnosis by enhancing early detection and accuracy. Techniques like deep learning, NLP-based models, Faster R-CNN, and CAD systems analyze medical data and images more effectively than manual methods. AI holds the potential to shape the future of pancreatic cancer diagnosis and improve patient outcomes.