Neural networks for medical image segmentation

Wei Chung Lin; Eric Chen Kuo Tsao; Chin Tu Chen; Yu Jen Feng

Neural networks for medical image segmentation

Wei Chung Lin^*, Eric Chen Kuo Tsao, Chin Tu Chen, Yu Jen Feng

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Contribution to journal › Conference article › peer-review

4 Scopus citations

Abstract

A class of Constraint Satisfaction Neural Networks (CSNN) is proposed for solving the problem of medical image segmentation which can be formulated as a Constraint Satisfaction Problem (CSP). The CSNN can be viewed as a collection of neurons that interconnect with each other. The connections and the topology of a CSNN are used to represent the constraints in a CSP. The mechanism of the neural network is to find a solution that satisfies all the constraints in order to achieve a global consistency. The final solution outlines segmented areas and simultaneously satisfies all the constraints. This technique has been applied to many images in different domains and the results show that this CSNN method is a very promising approach for image segmentation.

Original language	English (US)
Pages (from-to)	376-385
Number of pages	10
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1445
State	Published - Jan 1 1991
Event	Medical Imaging V: Image Processing - San Jose, CA, USA Duration: Feb 27 1991 → Mar 1 1991

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Cite this

@article{769f12f8ca4a4eb98b50d94e8aa58e35,

title = "Neural networks for medical image segmentation",

abstract = "A class of Constraint Satisfaction Neural Networks (CSNN) is proposed for solving the problem of medical image segmentation which can be formulated as a Constraint Satisfaction Problem (CSP). The CSNN can be viewed as a collection of neurons that interconnect with each other. The connections and the topology of a CSNN are used to represent the constraints in a CSP. The mechanism of the neural network is to find a solution that satisfies all the constraints in order to achieve a global consistency. The final solution outlines segmented areas and simultaneously satisfies all the constraints. This technique has been applied to many images in different domains and the results show that this CSNN method is a very promising approach for image segmentation.",

author = "Lin, {Wei Chung} and Tsao, {Eric Chen Kuo} and Chen, {Chin Tu} and Feng, {Yu Jen}",

year = "1991",

month = jan,

day = "1",

language = "English (US)",

volume = "1445",

pages = "376--385",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Medical Imaging V: Image Processing ; Conference date: 27-02-1991 Through 01-03-1991",

}

TY - JOUR

T1 - Neural networks for medical image segmentation

AU - Lin, Wei Chung

AU - Tsao, Eric Chen Kuo

AU - Chen, Chin Tu

AU - Feng, Yu Jen

PY - 1991/1/1

Y1 - 1991/1/1

N2 - A class of Constraint Satisfaction Neural Networks (CSNN) is proposed for solving the problem of medical image segmentation which can be formulated as a Constraint Satisfaction Problem (CSP). The CSNN can be viewed as a collection of neurons that interconnect with each other. The connections and the topology of a CSNN are used to represent the constraints in a CSP. The mechanism of the neural network is to find a solution that satisfies all the constraints in order to achieve a global consistency. The final solution outlines segmented areas and simultaneously satisfies all the constraints. This technique has been applied to many images in different domains and the results show that this CSNN method is a very promising approach for image segmentation.

AB - A class of Constraint Satisfaction Neural Networks (CSNN) is proposed for solving the problem of medical image segmentation which can be formulated as a Constraint Satisfaction Problem (CSP). The CSNN can be viewed as a collection of neurons that interconnect with each other. The connections and the topology of a CSNN are used to represent the constraints in a CSP. The mechanism of the neural network is to find a solution that satisfies all the constraints in order to achieve a global consistency. The final solution outlines segmented areas and simultaneously satisfies all the constraints. This technique has been applied to many images in different domains and the results show that this CSNN method is a very promising approach for image segmentation.

UR - http://www.scopus.com/inward/record.url?scp=0025841394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025841394&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0025841394

SN - 0277-786X

VL - 1445

SP - 376

EP - 385

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Medical Imaging V: Image Processing

Y2 - 27 February 1991 through 1 March 1991

ER -

Neural networks for medical image segmentation

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this