Skip to main content
. Author manuscript; available in PMC: 2021 Jul 22.
Published in final edited form as: Appl Sci (Basel). 2020 Sep 6;10(18):6187. doi: 10.3390/app10186187

Table 1.

Evaluation metrics on cell counting and segmentation achieved by ACDC (with and without bilateral filtering) on the analyzed time-lapse microscopy VU and 2018 DSB datasets, comprising 46 and 301 images, respectively. The results for the DSC and IoU metrics, as well as the execution time measurements, are expressed as mean value ± standard deviation.

Method Dataset Pearson Coeff. (p-Value) DSC (%) IoU (%) Exec. Time (s)
ACDC (without bilateral filter) VU ρ = 0.99 (p = 2.5 × 10−74) 75.86 ± 5.98 61.45 ± 7.47 3.98 ± 0.10
ACDC (with bilateral filter) VU ρ = 0.99 (p = 6.6 × 10−74) 76.84 ± 6.71 62.84 ± 8.58 7.49 ± 0.30

ACDC (without bilateral filter) DSB ρ = 0.96 (p = 1.1 × 10−175) 87.34 ± 6.89 77.97 ± 9.49 0.07 ± 0.05
ACDC (with bilateral filter) DSB ρ = 0.96 (p = 2.6 × 10−169) 88.64 ± 7.41 80.37 ± 10.58 0.12 ± 0.09