Disentangling chromosome overlaps by combining trainable shape models with classification evidence

Graham C. Charters; Jim Graham

doi:10.1109/TSP.2002.800421

Disentangling chromosome overlaps by combining trainable shape models with classification evidence

Graham C. Charters, Jim Graham

Research output: Contribution to journal › Article › peer-review

Abstract

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.

Original language	English
Pages (from-to)	2080-2085
Number of pages	5
Journal	IEEE Transactions on Signal Processing
Volume	50
Issue number	8
DOIs	https://doi.org/10.1109/TSP.2002.800421
Publication status	Published - Aug 2002

Keywords

Biological cells
Evidence combination
Image segmentation
Occlusion
Shape modeling

Access to Document

10.1109/TSP.2002.800421

Cite this

@article{4ec878752bb647f0a77cd2b37ccde83f,

title = "Disentangling chromosome overlaps by combining trainable shape models with classification evidence",

abstract = "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.",

keywords = "Biological cells, Evidence combination, Image segmentation, Occlusion, Shape modeling",

author = "Charters, {Graham C.} and Jim Graham",

year = "2002",

month = aug,

doi = "10.1109/TSP.2002.800421",

language = "English",

volume = "50",

pages = "2080--2085",

journal = "IEEE Transactions on Signal Processing",

publisher = "IEEE",

number = "8",

}

TY - JOUR

T1 - Disentangling chromosome overlaps by combining trainable shape models with classification evidence

AU - Charters, Graham C.

AU - Graham, Jim

PY - 2002/8

Y1 - 2002/8

N2 - 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.

AB - 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.

KW - Biological cells

KW - Evidence combination

KW - Image segmentation

KW - Occlusion

KW - Shape modeling

U2 - 10.1109/TSP.2002.800421

DO - 10.1109/TSP.2002.800421

M3 - Article

VL - 50

SP - 2080

EP - 2085

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

IS - 8

ER -

Disentangling chromosome overlaps by combining trainable shape models with classification evidence

Abstract

Keywords

Access to Document

Fingerprint

Cite this