Disentangling chromosome overlaps by combining trainable shape models with classification evidence

Disentangling chromosome overlaps by combining trainable shape models with classification evidence

Resolving chromosome overlaps is an unsolved problem in automated chromosome analysis. We propose a method that combines evidence from classification and shape, based on trainable shape models. In evaluation using synthesized overlaps, certain cases are resolvable using shape evidence alone, but whe...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on signal processing 2002-08, Vol.50 (8), p.2080-2085
Hauptverfasser: Charters, G.C., Graham, J.
Format: Artikel
Sprache:eng
Schlagworte:
Applied sciences
Automation
Biological cells
Biomedical engineering
Biomedical imaging
Exact sciences and technology
Image processing
Image segmentation
Information, signal and communications theory
Machine vision
Pattern analysis
Pattern recognition
Shape measurement
Signal processing
Solid modeling
Telecommunications and information theory
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Resolving chromosome overlaps is an unsolved problem in automated chromosome analysis. We propose a method that combines evidence from classification and shape, based on trainable shape models. In evaluation using synthesized overlaps, certain cases are resolvable using shape evidence alone, but where this is misleading, classification evidence improves performance.
ISSN:1053-587X
1941-0476
DOI:10.1109/TSP.2002.800421