Meeting Banner
Abstract #1772

Validation of Effectiveness of Multi-Parametric Endorectal MR Image Features for Prostate Cancer Detection and Correlation with Gleason Score

Yahui Peng1, Yulei Jiang1, Tatjana Antic2, Maryellen L. Giger1, Scott Eggener3, Aytekin Oto1

1Radiology, The University of Chicago, Chicago, IL, United States; 2Pathology, The University of Chicago, Chicago, IL, United States; 3Surgery, The University of Chicago, Chicago, IL, United States

We previously identified from Phillips MR images three quantitative multi-parametric endorectal MR image features effective for differentiation between prostate cancer and normal peripheral zone tissue regions of interest (ROIs), and moderately correlate with tumor ROI-specific Gleason score. We now validate these image features on GE MR images of 71 prostate cancer patients. Results show for both Philips and GE scanners that the 10th percentile, and average, ADC values, and T2-weighted signal-intensity histogram skewness are effective in differentiating prostate cancer from normal peripheral zone tissue ROIs, and that the ADC features correlate moderately and negatively with tumor ROI-specific Gleason scores.

Abstract PDF

Keywords

accepted acquisition aided although analyzed antic antigen apparent artifacts beneficial biopsy cancer candidates cause certain characteristic characteristics characterize characterized classifier clearly clinical clinically coefficient coefficients combination combined common computer conditionally contrast correlate correlation currently curve death detection development diagnosis differentiating differentiation diffusion discriminant distribution dynamic effective effectively effectiveness elevated enhanced error extracted features furthermore good guided highly histology identified independent intensity known leave limitations linear localization manufacturers moderately negatively operating parametric particularly pathologist pathology patients percentile performances peripheral post potentially practice previously promising proprietary prostate protocols quantitative radiologist radiology receiver relevant report respect respectively reversed robustness scanners score serve sets similarities skewness skin staging stem suggest suggests surgery terms tissue training tumor ultrasound undergone validation versa vice visually yang yielded zone