Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Accurate Detection of Dysmorphic Nuclei Using Dynamic Programming and Supervised Classification

Fig 7

Discrimination of dysmorphic nuclei based on elliptic Fourier descriptors.

(A) Morphology-based ranking of HDF-NCP nuclei. Both dysmorphic (red) and normal (blue) nuclei of HDF-NCP are ranked according to their summed EFD value (color coded). Severely deformed nuclei have higher EFD values than nuclei with small blebs, which in turn have larger EFD values than regular, ovoid-shaped nuclei. (B) Texture-based ranking for HDF-NULL cells. Dysmorphic nuclei are characterized by an intensity gradient due to an chromatin ruffling. Normal and aberrant nuclei of comparable shape (EFD value in italic and in brackets) can be distinguished based on the value of the entropy texture parameter (color coded).

Fig 7

doi: https://doi.org/10.1371/journal.pone.0170688.g007