Skip to main content
Fig. 8 | BMC Bioinformatics

Fig. 8

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

Fig. 8

Visual comparison of nuclei volumes measured in segmentation results of LoS, FARSight, 3D Watershed and ilastik. (a) Mouse embryo, (b) breast cancer spheroid and (c) pancreatic cancer spheroid. Spheres were plotted around each nucleus’ centroid position detected in the respective ground truth or by the respective segmentation method. The radius of each sphere in the ground truth represents the manually determined mean nuclei volume for a representative subset of nuclei. The spheres for the segmentation outputs represent the automatically determined volume for each detected nucleus. Coloring scheme: for each dataset, a minimum (purple) and an approximate maximum volume (red) across all results for LoS, FARsight, 3D Watershed and ilastik was determined (minimum volume for coloring: 1 μm3 for (a), (b) and (c); maximum volume for coloring: 1600 μm3 for (a), 4200 μm3 for (b) and 1000 μm3 for (c), respectively). Note: for better visualization, extreme outliers from the ilastik segmentation results were removed for determining the maximum volume: (one for (a), one for (b) and three for (c)). Subsequently, each sphere was assigned a color depending on its volume

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us