. 2020 Jul 29;9:e57613. doi: 10.7554/eLife.57613

Appendix 5—table 2. Average segmentation accuracy for different segmentation algorithms.

The average is computed from a set of seven specimen for the ovules and four for the lateral root primordia (LRP), while the error is measured by standard deviation. The segmentation is produced by multicut, GASP, mutex watershed (Mutex) and DT watershed (DTWS) clustering strategies. We additionally report the scores given by the lifted multicut on the LRP dataset. The Metrics used are the Adapted Rand error to asses the overall segmentation quality, the VOI_merge and VOI_split respectively assessing erroneous merge and splitting events (lower is better for all metrics). Source files used to create the table are available in the Appendix 5—table 2—source data 1.

Appendix 5—table 2—source data 1. Source data for the average segmentation accuracy of different segmentation algorithms in Appendix 5—table 2.

The archive contains CSV files with evaluation metrics computed on the Lateral Root and Ovules test sets. 'root_final_16_03_20_110904.csv' - evaluation metrics for the Lateral Root, 'ovules_final_16_03_20_113546.csv' - evaluation metrics for the Ovules.

elife-57613-app5-table2-data1.zip^{(129.7KB, zip)}

Segmentation	ARand	VOI_split	VOI_merge
Ovules
DTWS	0.135 0.036	0.585 0.042	0.320 0.089
GASP	0.114 0.059	0.357 0.066	0.354 0.109
MultiCut	0.145 0.080	0.418 0.069	0.429 0.124
Mutex	0.115 0.059	0.359 0.066	0.354 0.108
Lateral Root Primordia
DTWS	0.550 0.158	1.869 0.174	0.159 0.073
GASP	0.037 0.029	0.183 0.059	0.237 0.133
MultiCut	0.037 0.029	0.190 0.067	0.236 0.128
Lifted Multicut	0.040 0.039	0.162 0.068	0.287 0.207
Mutex	0.105 0.118	0.624 0.812	0.542 0.614