Premium
SU‐E‐J‐252: Reproducibility of Radiogenomic Image Features: Comparison of Two Semi‐Automated Segmentation Methods
Author(s) -
Lee M,
Woo B,
Kim J,
Jamshidi N,
Kuo M
Publication year - 2015
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4924338
Subject(s) - reproducibility , segmentation , fluid attenuated inversion recovery , magnetic resonance imaging , coefficient of variation , nuclear medicine , image segmentation , medicine , effective diffusion coefficient , artificial intelligence , computer science , radiology , pattern recognition (psychology) , biomedical engineering , mathematics , statistics
Purpose: Objective and reliable quantification of imaging phenotype is an essential part of radiogenomic studies. We compared the reproducibility of two semi‐automatic segmentation methods for quantitative image phenotyping in magnetic resonance imaging (MRI) of glioblastoma multiforme (GBM). Methods: MRI examinations with T1 post‐gadolinium and FLAIR sequences of 10 GBM patients were downloaded from the Cancer Image Archive site. Two semi‐automatic segmentation tools with different algorithms (deformable model and grow cut method) were used to segment contrast enhancement, necrosis and edema regions by two independent observers. A total of 21 imaging features consisting of area and edge groups were extracted automatically from the segmented tumor. The inter‐observer variability and coefficient of variation (COV) were calculated to evaluate the reproducibility. Results: Inter‐observer correlations and coefficient of variation of imaging features with the deformable model ranged from 0.953 to 0.999 and 2.1% to 9.2%, respectively, and the grow cut method ranged from 0.799 to 0.976 and 3.5% to 26.6%, respectively. Coefficient of variation for especially important features which were previously reported as predictive of patient survival were: 3.4% with deformable model and 7.4% with grow cut method for the proportion of contrast enhanced tumor region; 5.5% with deformable model and 25.7% with grow cut method for the proportion of necrosis; and 2.1% with deformable model and 4.4% with grow cut method for edge sharpness of tumor on CE‐T1W1. Conclusion: Comparison of two semi‐automated tumor segmentation techniques shows reliable image feature extraction for radiogenomic analysis of GBM patients with multiparametric Brain MRI.