Multi-Channel 3D Deep Learning Architectures for Evaluation of Prostate Lesion Detection
Dimitrios I. Zaridis, Eugenia Mylona, Nikolaos S. Tachos, Kostas Marias, Manolis Tsiknakis, Dimitrios I. Fotiadis · 2023
The localization of prostate cancer on MR images is of paramount importance for accurate diagnosis and treatment. In the present study, transformations of 3 Deep Learning segmentation models from 2D to 3D space are proposed to segment prostate lesions in MR images. The 3D Use-Net model is the best model outperforming the second by 10% Dice Score and 1.79mm Hausdorff Distance.