Program Information
Correlation Between Texture Analysis-Based Model Observer and Human Observer in Diagnosis of Ischemic Infarct in Non-Contrast Head CT of Adults
B Li*, A Fujita, K Buch, O Sakai, Boston University Medical Center, Boston, MA
Presentations
TU-G-204-6 (Tuesday, July 14, 2015) 4:30 PM - 6:00 PM Room: 204
Purpose: To investigate the correlation between texture analysis-based model observer and human observer in the task of diagnosis of ischemic infarct in non-contrast head CT of adults.
Methods: Non-contrast head CTs of five patients (2 M, 3 F; 58-83 y) with ischemic infarcts were retro-reconstructed using FBP and Adaptive Statistical Iterative Reconstruction (ASIR) of various levels (10-100%). Six neuro-radiologists reviewed each image and scored image quality for diagnosing acute infarcts by a 9-point Likert scale in a blinded test. These scores were averaged across the observers to produce the average human observer responses. The chief neuro-radiologist placed multiple ROIs over the infarcts. These ROIs were entered into a texture analysis software package. Forty-two features per image, including 11 GLRL, 5 GLCM, 4 GLGM, 9 Laws, and 13 2-D features, were computed and averaged over the images per dataset. The Fisher-coefficient (ratio of between-class variance to in-class variance) was calculated for each feature to identify the most discriminating features from each matrix that separate the different confidence scores most efficiently. The 15 features with the highest Fisher-coefficient were entered into linear multivariate regression for iterative modeling.
Results: Multivariate regression analysis resulted in the best prediction model of the confidence scores after three iterations (df=11, F=11.7, p-value<0.0001). The model predicted scores and human observers were highly correlated (R=0.88, R-sq=0.77). The root-mean-square and maximal residual were 0.21 and 0.44, respectively. The residual scatter plot appeared random, symmetric, and unbiased.
Conclusion: For diagnosis of ischemic infarct in non-contrast head CT in adults, the predicted image quality scores from texture analysis-based model observer was highly correlated with that of human observers for various noise levels. Texture-based model observer can characterize image quality of low contrast, subtle texture changes in addition to human observers.
Contact Email: