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 Selnæs^1,2, Jose Teruel¹, Brage Krüger-Stokke^1,3, Øystein Størkersen⁴, Helena Bertilsson ^5,6, May-Britt Tessem¹, Siver Andreas Moestue^1,2, and Tone Frost Bathen^1,2

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, K_trans, V_e and SUV) did not significantly improve the area under the receiver operating curve in comparison with an mpMRI-only model (features: T2W, ADC, K_trans, V_e), 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