Meeting Banner
Abstract #2750

Multimodality multiparametric 18F-Fluciclovine PET/MRI for computer-assisted detection of primary prostate cancer: is there a role for SUV?

Mattijs Elschot1, Elise Sandsmark1, Kirsten Margrete Selnæs1,2, Jose Teruel1, Brage Krüger-Stokke1,3, Øystein Størkersen4, Helena Bertilsson 5,6, May-Britt Tessem1, Siver Andreas Moestue1,2, and Tone Frost Bathen1,2

1Department of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, Norway, 2St Olavs Hospital, Trondheim, Norway, 3Department of Radiology, St Olavs Hospital, Trondheim, Norway, 4Department of Pathology, St Olavs Hospital, Trondheim, Norway, 5Department of Urology, St Olavs Hospital, Trondheim, Norway, 6Department of Cancer Research and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, Norway

Computer-assisted algorithms have been proposed to support radiological reading of multiparametric MRI (mpMRI) images for detection of localized primary prostate cancer. In this work, we investigated if standardized uptake values (SUV) from combined 18F-Fluciclovine PET/mpMRI can improve automated classification of tumor and non-tumor voxels. We found that a PET/mpMRI model (features: T2W, ADC, Ktrans, Ve and SUV) did not significantly improve the area under the receiver operating curve in comparison with an mpMRI-only model (features: T2W, ADC, Ktrans, Ve), suggesting limited additional value of SUV in voxel classification for computer-assisted detection of primary prostate cancer.

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

Join Here