Abstract #2724

Repeatability of Selected Multiparametric Prostate MRI Radiomics Features

Michael Schwier^1,2, Joost van Griethuysen³, Mark G Vangel^2,4, Steve Pieper⁵, Sharon Peled^1,2, Clare M Tempany^1,2, Hugo Aerts^2,6, Ron Kikinis^1,2, Fiona M Fennessy^1,2,6, and Andrey Fedorov^1,2

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