Meeting Banner
Abstract #2724

Repeatability of Selected Multiparametric Prostate MRI Radiomics Features

Michael Schwier1,2, Joost van Griethuysen3, Mark G Vangel2,4, Steve Pieper5, Sharon Peled1,2, Clare M Tempany1,2, Hugo Aerts2,6, Ron Kikinis1,2, Fiona M Fennessy1,2,6, and Andrey Fedorov1,2

1Brigham and Women's Hospital, Boston, MA, United States, 2Harvard Medical School, Boston, MA, United States, 3Netherlands Cancer Institute / Maastricht University, Amsterdam, Netherlands, 4Massachusetts General Hospital, Charlestown, MA, United States, 5Isomics, Inc., Cambridge, MA, United States, 6Dana-Farber Cancer Institute, Boston, MA, United States

In this study we assess the repeatability of selected radiomics features for small prostate tumors in ADC and T2-weighted images. We used a prostate mpMRI test-retest dataset for our evaluation. Different configurations of preprocessing were compared. The intraclass correlation coefficient was employed as a measure of repeatability. Our results show that several of the selected features have good repeatability, however, only when specific preprocessing was applied. Based on our data, texture computation should be done in 2D. Normalization improves repeatability for ADC features, but not in T2-weighted images.

This abstract and the presentation materials are available to members only; a login is required.

Join Here