Tumor regions, with their associated Gleason score, were manually delineated within the anatomical map, facilitating the direct coregistration between regions of interest in PET and histopathology; this approach was similar to that used in previous works [40, 43, 44].
In each case, regions-of-interest (ROIs) were manually delineated in accordance with Franklin and Paxinos atlas [ 44] and for each ROI the percentage of DAB-labeled area was calculated.
In accordance with previous reports, we found that the volume reproducibility of manually delineated lesions correlated negatively with their size [ 26, 27].
Next, the validity of our approach is tested through the segmentation of different cardiac CT scans and the subsequent comparison of the results with manually delineated ground truth.
Segmentation results are validated through the comparison with manually delineated ground truth, both qualitatively (no noticeable errors found after visual inspection) and quantitatively (mass overlapping over 90%).
The geospatial tool successfully delineated the streambanks for both rivers in less than 10 min with a mean error ranging from 0.3 m to 10.3 m when compared with five manually delineated streambanks.
a MR image with b manually delineated morphological tumour volume.
The segmenting efficiency was compared with the manually delineated ground truth data N R in Figure 3(a) by using OM which was defined as (14) OM = 2 N T ∩ N R N T + N R, where N T indicates the pixels/voxels of the segmented coronary arteries.
Each CT scan slice was manually delineated and gas volume was computed with custom-made software.
Each of the mounds, confirmed in the orthoimages overlaid with the DEMs, was manually delineated using ArcGIS, and then, the mean elevation values along the outlines and the areas and the maximum elevation values inside each outline were measured.
