Ghent University Academic Bibliography

Advanced

Accurate detection of dysmorphic nuclei using dynamic programming and supervised classification

Marlies Verschuuren, Jonas De Vylder, Hannes Catrysse, Joke Robijns, Wilfried Philips UGent and Winnok De Vos UGent (2017) PLOS ONE. 12(1).
abstract
A vast array of pathologies is typified by the presence of nuclei with an abnormal morphology. Dysmorphic nuclear phenotypes feature dramatic size changes or foldings, but also entail much subtler deviations such as nuclear protrusions called blebs. Due to their unpredictable size, shape and intensity, dysmorphic nuclei are often not accurately detected in standard image analysis routines. To enable accurate detection of dysmorphic nuclei in confocal and widefield fluorescence microscopy images, we have developed an automated segmentation algorithm, called Blebbed Nuclei Detector (BleND), which relies on two-pass thresholding for initial nuclear contour detection, and an optimal path finding algorithm, based on dynamic programming, for refining these contours. Using a robust error metric, we show that our method matches manual segmentation in terms of precision and outperforms state-of-the-art nuclear segmentation methods. Its high performance allowed for building and integrating a robust classifier that recognizes dysmorphic nuclei with an accuracy above 95%. The combined segmentation-classification routine is bound to facilitate nucleus-based diagnostics and enable real-time recognition of dysmorphic nuclei in intelligent microscopy workflows.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
segmentation, microscopy, image analysis, computer vision
journal title
PLOS ONE
PLoS One
volume
12
issue
1
article number
e0170688
pages
19 pages
ISSN
1932-6203
DOI
10.1371/journal.pone.0170688
UGent publication?
yes
classification
A1
copyright statement
I have retained and own the full copyright for this publication
id
8505915
handle
http://hdl.handle.net/1854/LU-8505915
date created
2017-01-27 13:01:28
date last changed
2017-02-02 12:52:04
@article{8505915,
  abstract     = {A vast array of pathologies is typified by the presence of nuclei with an abnormal morphology. Dysmorphic nuclear phenotypes feature dramatic size changes or foldings, but also entail much subtler deviations such as nuclear protrusions called blebs. Due to their unpredictable size, shape and intensity, dysmorphic nuclei are often not accurately detected in standard image analysis routines. To enable accurate detection of dysmorphic nuclei in confocal and widefield fluorescence microscopy images, we have developed an automated segmentation algorithm, called Blebbed Nuclei Detector (BleND), which relies on two-pass thresholding for initial nuclear contour detection, and an optimal path finding algorithm, based on dynamic programming, for refining these contours. Using a robust error metric, we show that our method matches manual segmentation in terms of precision and outperforms state-of-the-art nuclear segmentation methods. Its high performance allowed for building and integrating a robust classifier that recognizes dysmorphic nuclei with an accuracy above 95\%. The combined segmentation-classification routine is bound to facilitate nucleus-based diagnostics and enable real-time recognition of dysmorphic nuclei in intelligent microscopy workflows.},
  articleno    = {e0170688},
  author       = {Verschuuren, Marlies and De Vylder, Jonas and Catrysse, Hannes and Robijns, Joke and Philips, Wilfried and De Vos, Winnok},
  issn         = {1932-6203},
  journal      = {PLOS ONE},
  keyword      = {segmentation,microscopy,image analysis,computer vision},
  number       = {1},
  pages        = {19},
  title        = {Accurate detection of dysmorphic nuclei using dynamic programming and supervised classification},
  url          = {http://dx.doi.org/10.1371/journal.pone.0170688},
  volume       = {12},
  year         = {2017},
}

Chicago
Verschuuren, Marlies, Jonas De Vylder, Hannes Catrysse, Joke Robijns, Wilfried Philips, and Winnok De Vos. 2017. “Accurate Detection of Dysmorphic Nuclei Using Dynamic Programming and Supervised Classification.” Plos One 12 (1).
APA
Verschuuren, M., De Vylder, J., Catrysse, H., Robijns, J., Philips, W., & De Vos, W. (2017). Accurate detection of dysmorphic nuclei using dynamic programming and supervised classification. PLOS ONE, 12(1).
Vancouver
1.
Verschuuren M, De Vylder J, Catrysse H, Robijns J, Philips W, De Vos W. Accurate detection of dysmorphic nuclei using dynamic programming and supervised classification. PLOS ONE. 2017;12(1).
MLA
Verschuuren, Marlies, Jonas De Vylder, Hannes Catrysse, et al. “Accurate Detection of Dysmorphic Nuclei Using Dynamic Programming and Supervised Classification.” PLOS ONE 12.1 (2017): n. pag. Print.