Related Experiment Video
Updated: Feb 28, 2026
DIPLOMA Approach for Standardized Pathology Assessment of Distal Pancreatectomy Specimens
Published on: February 1, 2020
CT texture features are associated with overall survival in pancreatic ductal adenocarcinoma - a quantitative
Armin Eilaghi1,2, Sameer Baig1, Yucheng Zhang1
1Department of Medical Imaging and Sunnybrook Research Institute, Sunnybrook Health Sciences Center, University of Toronto, 2075 Bayview Ave., Room Rm AG 46, Toronto, M4N 3 M5, ON, Canada.
Background:
To assess whether CT-derived texture features predict survival in patients undergoing resection for pancreatic ductal adenocarcinoma (PDAC).
Methods:
Thirty patients with pre-operative CT from 2007 to 2012 for PDAC were included. Tumor size and five texture features namely uniformity, entropy, dissimilarity, correlation, and inverse difference normalized were calculated. Mann-Whitney rank sum test was used to compare tumor with normal pancreas. Receiver operating characteristics (ROC) analysis, Cox regression and Kaplan-Meier tests were used to assess association of texture features with overall survival (OS).
Results:
Uniformity (p < 0.001), entropy (p = 0.009), correlation (p < 0.001), and mean intensity (p < 0.001) were significantly different in tumor regions compared to normal pancreas. Tumor dissimilarity (p = 0.045) and inverse difference normalized (p = 0.046) were associated with OS whereas tumor intensity (p = 0.366), tumor size (p = 0.611) and other textural features including uniformity (p = 0.334), entropy (p = 0.330) and correlation (p = 0.068) were not associated with OS.
Conclusion:
CT-derived PDAC texture features of dissimilarity and inverse difference normalized are promising prognostic imaging biomarkers of OS for patients undergoing curative intent surgical resection.
