Pancreatic cancer CT AI research,with links to the evidence.

Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation

Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation

Deep learning to distinguish pancreatic cancer tissue from non-cancerous pancreatic tissue: a retrospective study with cross-racial external validation.

Some pancreatic tumors smaller than 2 cm may be missed on CT; the cited study reports results for a defined study population. A CNN distinguished pancreatic cancer tissue with 97.3–99.0% sensitivity and AUC 0.997–0.999 on local test sets, and 79.0% sensitivity / AUC 0.920 on a U.S. dataset. CNN outperformed radiologists (98.3% vs. 92.9%), correctly classified 11 of 12 radiologist-missed cancers (92%), and reached 92.1% sensitivity for tumors under 2 cm.

Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study

Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study

Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study.

The cited study reports that some pancreatic tumors under 2 cm may be missed on abdominal CT. An end-to-end deep-learning tool (segmentation CNN plus an ensemble of five CNNs) achieved 89.9% sensitivity, 95.9% specificity, and AUC 0.96 internally. Across 1,473 nationwide real-world CT studies (669 malignant, 804 controls), it achieved 89.7% sensitivity, 92.8% specificity, and AUC 0.95, with 74.7% sensitivity for tumors under 2 cm.

Radiomic Features at CT Can Distinguish Pancreatic Cancer from Noncancerous Pancreas

Radiomic Features at CT Can Distinguish Pancreatic Cancer from Noncancerous Pancreas

Radiomic Features at CT Can Distinguish Pancreatic Cancer from Noncancerous Pancreas.

XGBoost radiomic analysis of CT patches distinguished PDAC from noncancerous pancreas. The generalized model (trained on Taiwan and U.S. cohorts) reached 94.7% sensitivity / 95.4% specificity / AUC 0.98 on the Taiwanese test set, and 80.6% / 100% / AUC 0.91 on the U.S. test set. PDACs showed lower intensity and higher heterogeneity radiomic features.

Detection of pancreatic cancer with two- and three-dimensional radiomic analysis in a nationwide population-based real-world dataset

Detection of pancreatic cancer with two- and three-dimensional radiomic analysis in a nationwide population-based real-world dataset

Detection of pancreatic cancer with two- and three-dimensional radiomic analysis in a nationwide population-based real-world dataset.

An automatic end-to-end CAD tool combining 2D and 3D radiomic machine-learning analysis reached 91.8% sensitivity, 82.2% specificity, and AUC 0.947 in 1,477 nationwide CT studies (671 cancer cases, 806 controls), with 70.7% sensitivity for tumors under 2 cm. Running 2D and 3D analyses in series raised specificity to 95.2%.

Applications of artificial intelligence in pancreatic and biliary diseases

Applications of artificial intelligence in pancreatic and biliary diseases

Applications of artificial intelligence in pancreatic and biliary diseases.

A concise review of major AI methodologies (machine learning, deep learning) and the current landscape of AI research in pancreatobiliary diseases — where diagnosis and treatment selection are often complex — covering detection/diagnosis, risk stratification and prognosis prediction to supplement clinicians.

Artificial Intelligence for Early Detection of Pancreatic Cancer in Prediagnostic and Diagnostic Computed Tomography Examinations: A Multicenter Retrospective Case-control Study

Artificial Intelligence for Early Detection of Pancreatic Cancer in Prediagnostic and Diagnostic Computed Tomography Examinations: A Multicenter Retrospective Case-control Study

Andre Yanchen Yeh, Dawei Chang, Pochuan Wang, Yenjia Chen, Kao-Lang Liu, Holger Roth, Hsu-Heng Yen, David Yen-Ting Chen, Po-Ting Chen*, Wei-Chih Liao, Weichung Wang.

A multicenter retrospective case-control study evaluated an AI tool on contrast-enhanced CT, including scans obtained 1–12 months before clinical diagnosis. It assessed pancreatic cancer detection against normal pancreas and other pancreatic diseases.

A multicenter retrospective case-control study evaluated an AI tool on contrast-enhanced CT, including scans obtained 1–12 months before clinical diagnosis. It assessed pancreatic cancer detection against normal pancreas and other pancreatic diseases.