Radiomics model-based algorithm for preoperative prediction of pancreatic ductal adenocarcinoma grade.

Valeriya S TikhonovaGrigory G KarmazanovskyEvvgeny V KondratyevIvan S GruzdevKseniya A MikhaylyukMikhail Yegorovich SinelnikovAmiran Sh Revishvili

Published in: European radiology (2022)

• A diagnostic algorithm based on CT texture features for preoperative PDAC grade prediction was developed. • The assumption that the scanning protocol can influence the results of texture analysis was confirmed and assessed. • Our results show that tumor differentiation grade can be assessed with sufficient diagnostic accuracy using CT texture analysis presented in this study.

Keyphrases

contrast enhanced
computed tomography
machine learning
magnetic resonance imaging
patients undergoing
randomized controlled trial
deep learning
image quality
dual energy
positron emission tomography
neural network
data analysis