Skip to main content

Table 5 Confusion matrix for 2D HeLa cell (A) and 3D HeLa cell (B) images using optimal majority-voting ensemble classifier with feature set SLF16 (A) and SLF10 (B) respectively. (Due to rounding, each row may not sum to 100). The average accuracy was 92.3% for 2D images (A) and 95.8% for 3D images (B).

From: Boosting accuracy of automated classification of fluorescence microscope images for location proteomics

A)
  DNA ER Gia Gpp Lam Mit Nuc Act TfR Tub  
DNA 98.9 1.2 0 0 0 0 0 0 0 0  
ER 0 96.5 0 0 0 2.3 0 0 0 1.2  
Gia 0 0 90.8 6.9 0 0 0 0 2.3 0  
Gpp 0 0 14.1 82.4 0 0 2.4 0 1.2 0  
Lam 0 0 1.2 0 88.1 1.2 0 0 9.5 0  
Mit 0 2.7 0 0 0 91.8 0 0 2.7 2.7  
Nuc 0 0 0 0 0 0 98.8 0 1.3 0  
Act 0 0 0 0 0 0 0 100 0 0  
TfR 0 1.1 0 0 12.1 2.2 0 1.1 81.3 2.2  
Tub 1.1 2.2 0 0 0 1.1 0 0 1.1 94.5  
B)
  Cyt DNA ER Gia Gpp Lam Mit Nuc Act TfR Tub
Cyt 100 0 0 0 0 0 0 0 0 0 0
DNA 0 98.1 0 0 0 0 0 1.9 0 0 0
ER 0 0 96.6 0 0 0 0 0 1.7 0 1.7
Gia 0 0 0 98.2 0 1.9 0 0 0 0 0
Gpp 0 0 0 4 96.0 0 0 0 0 0 0
Lam 0 0 0 1.8 1.8 96.4 0 0 0 0 0
Mit 0 0 0 3.5 0 0 94.7 0 1.8 0 0
Nuc 0 0 0 0 0 0 0 100 0 0 0
Act 0 0 1.7 0 0 0 1.7 0 94.8 1.7 0
TfR 0 0 0 0 0 5.7 3.8 0 1.9 84.9 3.8
Tub 0 0 3.7 0 0 0 0 0 0 1.9 94.4
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us