Pathological Validation of a Model Based on Diffusion Weighted Imaging and Dynamic Contrast-Enhanced MRI for Tumor Delineation in the Prostate Peripheral Zone

Greetje Groenendaal¹, ², Alie Borren², Maaike Moman², Evelyn Monninkhof³, Paul van Diest⁴, Marille Philippens², Marco van Vulpen², Uulke van der Heide¹,<sup

For the purpose of focal boost radiotherapy a voxel-wise tumor prediction model was developed for the prostate peripheral zone (PZ) using diffusion weighted imaging and dynamic contrast-enhanced MRI. This model showed an area under the receiver operating curve of 0.89 on a voxel level when validated with whole-mount section histopathology. The voxel size used was 2.5x2.5x2.5 mm3 The model output can be used to define different risk levels for tumor presence, which in turn could serve as an input for dose planning. In this way the robustness of tumor delineations for focal boost therapy can be greatly improved.