Robust and automated three-dimensional segmentation of densely packed cell nuclei in different biological specimens with Lines-of-Sight decomposition

Table 1 Algorithmic performance of LoS, FARSight, 3D Watershed and ilastik

Dataset	# cells GT	Algorithm	# cells Seg	Match	Recall	Precision	Accuracy	F-measure
Mouse embryo	61	LoS	59	58	0.95	0.98	0.94	0.97
		FARSight	62	60	0.98	0.97	0.95	0.98
		3D Watershed	299	61	1.00	0.20	0.20	0.34
		ilastik	274	61	1.00	0.22	0.22	0.36
Breast cancer spheroid	240	LoS	247	216	0.90	0.87	0.80	0.89
		FARSight	338	236	0.98	0.70	0.69	0.82
		3D Watershed	288	220	0.92	0.76	0.71	0.83
		ilastik	112	74	0.31	0.66	0.27	0.42
Pancreatic cancer spheroid	531	LoS	690	523	0.98	0.76	0.75	0.86
		FARSight	997	524	0.99	0.53	0.52	0.69
		3D Watershed	734	518	0.98	0.70	0.69	0.81
		ilastik	19744	531	1.00	0.03	0.03	0.05

Performance was measured against manually segmented ground truth for the three different test datasets. “# cells GT”, “# cells Seg” and “Match” list the number of cells that were determined manually in the ground truth, segmented by the different algorithms, and matched, respectively. The segmentation performance is given in terms of the metrics “Recall”, “Precision”, “Accuracy” and “F-measure”. Thereby, values range from 0 (worst performance) to 1 (best performance). For the LoS algorithm the same set of parameter values was used for all test images. For 3D Watershed and FARSight different parameter sets had to be used. These were determined by parameter scanning

ISSN: 1471-2105