Evolutionary algorithms in the classification of mammograms

D. C. Hope; E. Munday; S. L. Smith

Evolutionary algorithms in the classification of mammograms

Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The application of pattern recognition techniques to radiology has the potential to detect cancer earlier and save lives, and consequently much research has been devoted to this problem. This worked tackled a subset of the problem, investigating a novel method of classifying mammograms using an evolutionary approach known as Cartesian Genetic Programming (CGP). Microcalcifications, one of two major indicators of cancer on mammograms, were used for the classification. A large software framework was written in order to investigate this, which allows the viewing of images, manual segmentation of lesions and then automatic classification. Two classification approaches were pursued, the first classifying on texture features and the second, a new approach, classifying by using the lesion's raw pixel array. Early results using the system showed some potential. It was found that during training, networks could obtain correct classification rates of between 80 and 100%. The best results were approaching those in the contemporary literature and suggest the technique warrants further investigation.

Original language	English
Title of host publication	2007 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN IMAGE AND SIGNAL PROCESSING
Place of Publication	NEW YORK
Publisher	IEEE
Pages	258-265
Number of pages	8
ISBN (Print)	978-1-4244-0707-1
Publication status	Published - 2007
Event	IEEE Symposium on Computational Intelligence in Image and Signal Processing - Honolulu Duration: 1 Apr 2007 → 5 Apr 2007

Conference

Conference	IEEE Symposium on Computational Intelligence in Image and Signal Processing
City	Honolulu
Period	1/04/07 → 5/04/07

Keywords

COMPUTER-AIDED DETECTION
MICROCALCIFICATIONS

Cite this

@inproceedings{2781e212bdf54f9ab23a93e2091e346d,

title = "Evolutionary algorithms in the classification of mammograms",

abstract = "The application of pattern recognition techniques to radiology has the potential to detect cancer earlier and save lives, and consequently much research has been devoted to this problem. This worked tackled a subset of the problem, investigating a novel method of classifying mammograms using an evolutionary approach known as Cartesian Genetic Programming (CGP). Microcalcifications, one of two major indicators of cancer on mammograms, were used for the classification. A large software framework was written in order to investigate this, which allows the viewing of images, manual segmentation of lesions and then automatic classification. Two classification approaches were pursued, the first classifying on texture features and the second, a new approach, classifying by using the lesion's raw pixel array. Early results using the system showed some potential. It was found that during training, networks could obtain correct classification rates of between 80 and 100%. The best results were approaching those in the contemporary literature and suggest the technique warrants further investigation.",

keywords = "COMPUTER-AIDED DETECTION, MICROCALCIFICATIONS",

author = "Hope, {D. C.} and E. Munday and Smith, {S. L.}",

year = "2007",

language = "English",

isbn = "978-1-4244-0707-1",

pages = "258--265",

booktitle = "2007 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN IMAGE AND SIGNAL PROCESSING",

publisher = "IEEE",

address = "United States",

note = "IEEE Symposium on Computational Intelligence in Image and Signal Processing ; Conference date: 01-04-2007 Through 05-04-2007",

}

TY - GEN

T1 - Evolutionary algorithms in the classification of mammograms

AU - Hope, D. C.

AU - Munday, E.

AU - Smith, S. L.

PY - 2007

Y1 - 2007

N2 - The application of pattern recognition techniques to radiology has the potential to detect cancer earlier and save lives, and consequently much research has been devoted to this problem. This worked tackled a subset of the problem, investigating a novel method of classifying mammograms using an evolutionary approach known as Cartesian Genetic Programming (CGP). Microcalcifications, one of two major indicators of cancer on mammograms, were used for the classification. A large software framework was written in order to investigate this, which allows the viewing of images, manual segmentation of lesions and then automatic classification. Two classification approaches were pursued, the first classifying on texture features and the second, a new approach, classifying by using the lesion's raw pixel array. Early results using the system showed some potential. It was found that during training, networks could obtain correct classification rates of between 80 and 100%. The best results were approaching those in the contemporary literature and suggest the technique warrants further investigation.

AB - The application of pattern recognition techniques to radiology has the potential to detect cancer earlier and save lives, and consequently much research has been devoted to this problem. This worked tackled a subset of the problem, investigating a novel method of classifying mammograms using an evolutionary approach known as Cartesian Genetic Programming (CGP). Microcalcifications, one of two major indicators of cancer on mammograms, were used for the classification. A large software framework was written in order to investigate this, which allows the viewing of images, manual segmentation of lesions and then automatic classification. Two classification approaches were pursued, the first classifying on texture features and the second, a new approach, classifying by using the lesion's raw pixel array. Early results using the system showed some potential. It was found that during training, networks could obtain correct classification rates of between 80 and 100%. The best results were approaching those in the contemporary literature and suggest the technique warrants further investigation.

KW - COMPUTER-AIDED DETECTION

KW - MICROCALCIFICATIONS

M3 - Conference contribution

SN - 978-1-4244-0707-1

SP - 258

EP - 265

BT - 2007 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN IMAGE AND SIGNAL PROCESSING

PB - IEEE

CY - NEW YORK

T2 - IEEE Symposium on Computational Intelligence in Image and Signal Processing

Y2 - 1 April 2007 through 5 April 2007

ER -