![\"Example](\"https:\/\/wiki.cancerimagingarchive.net\/download\/attachments\/embedded-page\/DOI\/High%20Resolution%20Prostate%20Segmentations%20for%20the%20ProstateX-Challenge%20(PROSTATEx-Seg-HiRes)\/High%20Resolution.JPG?api=v2\")
<\/span><\/p>We created 66 high resolution segmentations for randomly chosen T2-weighted volumes of the\u00a0SPIE-AAPM-NCI PROSTATEx Challenges (PROSTATEx)<\/a>. The high\u00a0resolution segmentations were obtained\u00a0<\/span>by\u00a0<\/span>considering the three scan directions: for each scan direction (axial, sagittal, coronal),\u00a0<\/span>the gland was manually delineated by a medical student, followed\u00a0<\/span>by a review and corrections of an expert urologist.\u00a0<\/span>These three anisotropic segmentations were fused to one isotropic segmentation by means of shape-based interpolation\u00a0<\/span>in the following manner: (1) The signed distance transformation of the three segmentations is computed.\u00a0<\/span>(2) The anisotropic distance volumes are transformed into an isotropic high-resolution representation with linear interpolation. (3) By averaging the distances, smoothing and thresholding them at zero, we obtained the fused segmentation. <\/span>The resulting segmentations were manually verified and corrected further by the expert urologist if necessary.\u00a0<\/span>Serving as ground truth for training CNNs, these segmentations have the potential to improve the segmentation accuracy of automated algorithms. By considering not only the axial scans but also sagittal and coronal scan directions, we aimed to have higher fidelity of the segmentations especially at the apex and base regions of the prostate.<\/span><\/p> The segmentations to standard DICOM representation were created with dcmqi<\/a> <\/em>.<\/p> Acknowledgements<\/strong><\/span><\/p>