Table 3.
Time (entire volume) | Voxel based | Object based | |||||
---|---|---|---|---|---|---|---|
Type I | Type II | Accuracy | Precision | Recall | F1 | ||
DeepSynth | 37 sec | 5.92% | 1.79% | 92.30% | 87.09% | 98.45% | 92.42% |
FARSIGHT Default | 26 sec | 4.21% | 1.72% | 94.07% | 64.69% | 91.92% | 75.94% |
FARSIGHT Optimized | 26 sec | 4.18% | 1.78% | 94.04% | 86.45% | 92.58% | 89.41% |
Squassh Default | 10 min | 4.46% | 0.70% | 94.84% | 91.70% | 75.47% | 82.79% |
Squassh Optimized | 10 min | 3.19% | 1.31% | 95.50% | 94.49% | 74.53% | 83.33% |
CellProfiler Default | 10 min | 2.66% | 3.39% | 93.95% | 85.49% | 73.65% | 79.13% |
CellProfiler Optimized | 10 min | 2.76% | 2.34% | 94.90% | 83.49% | 89.33% | 86.31% |
Otsu- 3DWatershed | 29 sec | 2.53% | 3.51% | 93.95% | 82.59% | 76.37% | 79.36% |
The values for “Time” reflect the times required to obtain segmentations using. Accuracy was measured using both voxel-based metrics (voxel-by-voxel agreement with ground-truth data) and object-based metrics (agreement in the detection of objects with ground-truth data) for the entire 3D volume. For voxel-based accuracy, type-I error (false positive rate) represents the fraction of voxels in the volume wrongly detected as belonging to nuclei and type-II error (false negative rate) represents the fraction of voxels wrongly detected as background. Object-based accuracy is measured using the F1 score, which is the harmonic mean of precision and recall, where precision is the ratio of the number of correctly identified nuclei to the sum of the number of correctly identified nuclei plus the number of objects incorrectly identified as nuclei and recall is the ratio of the number of correctly identified nuclei to the sum of the number of correctly identified nuclei plus the number of nuclei that failed to be detected. Details of the analyses are described in “Methods”.