Table 2.
NetMets Mayerich et al. (2012) scores on the Brightfield dataset.
| OURS | BRF1 | BRF2 | BRF3 | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.05 | 0.29 | 0.71 | 0.65 | 0.11 | 0.29 | 0.81 | 0.78 | 0.07 | 0.28 | 0.77 | 0.70 | |
| k-MST Turetken et al. (2011) | 0.10 | 0.44 | 0.79 | 0.88 | 0.11 | 0.53 | 0.84 | 0.91 | 0.13 | 0.35 | 0.81 | 0.92 |
| Focus Narayanaswamy et al. (2011) | 0.39 | 0.54 | 0.75 | 1.00 | 0.49 | 0.53 | 0.90 | 1.00 | 0.38 | 0.46 | 0.74 | 1.00 |
| OSnake Wang et al. (2011) | 0.66 | 0.63 | 0.98 | 0.99 | 0.66 | 0.59 | 0.99 | 1.00 | 0.69 | 0.38 | 0.95 | 0.99 |
| APP2 Xiao et al. (2013) | 0.68 | 0.64 | 1.00 | 1.00 | 0.63 | 0.54 | 1.00 | 1.00 | 0.65 | 0.49 | 1.00 | 1.00 |
The NetMets software outputs four values for each trial, which are geometric False Positive Rate (FPR), geometric False Negative Rate (FNR), connectivity FPR, and connectivity FNR, respectively from left to right. Lower scores are better. The best scores are shown in bold face.