Journal
EUROPEAN RADIOLOGY
Volume 28, Issue 4, Pages 1520-1528Publisher
SPRINGER
DOI: 10.1007/s00330-017-5111-6
Keywords
CT texture analysis; Hepatic metastases; Colorectal cancer; CT; Colorectal metastases
Funding
- NIH National Center for Advancing Translational Sciences (NCATS) [UL1TR000427]
Ask authors/readers for more resources
To determine if identifiable hepatic textural features are present at abdominal CT in patients with colorectal cancer (CRC) prior to the development of CT-detectable hepatic metastases. Four filtration-histogram texture features (standard deviation, skewness, entropy and kurtosis) were extracted from the liver parenchyma on portal venous phase CT images at staging and post-treatment surveillance. Surveillance scans corresponded to the last scan prior to the development of CT-detectable CRC liver metastases in 29 patients (median time interval, 6 months), and these were compared with interval-matched surveillance scans in 60 CRC patients who did not develop liver metastases. Predictive models of liver metastasis-free survival and overall survival were built using regularised Cox proportional hazards regression. Texture features did not significantly differ between cases and controls. For Cox models using all features as predictors, all coefficients were shrunk to zero, suggesting no association between any CT texture features and outcomes. Prognostic indices derived from entropy features at surveillance CT incorrectly classified patients into risk groups for future liver metastases (p < 0.001). On surveillance CT scans immediately prior to the development of CRC liver metastases, we found no evidence suggesting that changes in identifiable hepatic texture features were predictive of their development. aEuro cent No correlation between liver texture features and metastasis-free survival was observed. aEuro cent Liver texture features incorrectly classified patients into risk groups for liver metastases. aEuro cent Standardised texture analysis workflows need to be developed to improve research reproducibility.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available