Curvelet initialized level set cell segmentation for touching cells in low contrast images

Highlights • A method to segment touching cells in very low contrast cell images has been proposed. • To improve contrast multiscale top-hat transform and h-maxima has been proposed. • Curvelet initialized modified Chan-Vese model has been proposed for segmentation. • The enhancement results of the...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computerized medical imaging and graphics 2016-04, Vol.49, p.46-57
Hauptverfasser:	Kaur, Sarabpreet, Sahambi, J.S
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Boundaries Cell Membrane - ultrastructure Cell Nucleus - ultrastructure Cell segmentation Cell Tracking - methods Curvelets Female h-maxima Humans Image contrast Image enhancement Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Internal Medicine Level sets Medical imaging Microscopy - methods Multiscale top hat transform Nuclei Other Pattern Recognition, Automated - methods Performance measurement Reproducibility of Results Segmentation Sensitivity and Specificity Signal to noise ratio Uterine Cervical Neoplasms - diagnostic imaging Wavelet Analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Highlights • A method to segment touching cells in very low contrast cell images has been proposed. • To improve contrast multiscale top-hat transform and h-maxima has been proposed. • Curvelet initialized modified Chan-Vese model has been proposed for segmentation. • The enhancement results of the proposed method have been verified using PSNR. • Accuracy, precision and sensitivity validate the proposed segmentation method.
ISSN:	0895-6111 1879-0771
DOI:	10.1016/j.compmedimag.2016.01.002