Appendix 5—table 3. Average segmentation accuracy on leaf surfaces.

The evaluation was computed on six specimen (data available under: https://osf.io/kfx3d) with the segmentation methodology presented in section Analysis of leaf growth and differentiation. The Metrics used are: the ARand error to asses the overall segmentation quality, the VOI_merge and VOI_split assessing erroneous merge and splitting events respectively, and accuracy (Accu.) measured as percentage of correctly segmented cells (lower is better for all metrics except accuracy). For the Proj3D method a limited number of cells (1.04% mean across samples) was missing due to segmentation errors and required manual seeding. While it is not possible to quantify the favorable impact on the ARand and VOIs scores, we can assert that the Proj3D accuracy has been overestimated by approximately 1.04%.

Segmentation	ARand	VOIsplit	VOImerge	Accu. (%)	ARand	VOIsplit	VOImerge	Accu. (%)
	Sample 1 (Arabidopsis, Col0_07 T1)				Sample 2 (Arabidopsis, Col0_07 T2)
PredAutoSeg	0.387	0.195	0.385	91.561	0.269	0.171	0.388	89.798
Proj3D	0.159	0.076	0.273	82.700	0.171	0.078	0.279	84.697
RawAutoSeg	0.481	0.056	0.682	75.527	0.290	0.064	0.471	75.198
	Sample 3 (Arabidopsis, Col0_03 T1)				Sample 4 (Arabidopsis, Col0_03 T2)
PredAutoSeg	0.079	0.132	0.162	90.651	0.809	0.284	0.944	90.520
Proj3D	0.065	0.156	0.138	88.655	0.181	0.228	0.406	91.091
RawAutoSeg	0.361	0.101	0.412	88.130	0.295	0.231	0.530	85.037
	Sample 5 (Cardamine, Ox T1)				Sample 6 (Cardamine, Ox T2)
PredAutoSeg	0.087	0.162	0.125	98.858	0.052	0.083	0.077	97.093
Proj3D	0.051	0.065	0.066	95.958	0.037	0.060	0.040	98.470
RawAutoSeg	0.429	0.043	0.366	93.937	0.267	0.033	0.269	89.288