Classification of mammographic breast density by the histogram approach using neural networks

Sachiko Goto, Yoshiharu Azuma, Tetsuhiro Sumimoto, Shigeru Eiho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Our aim was to improve the accuracy of classifying x-ray mammographic breast densities. The histogram approach using the neural network was used for the purpose of constructing a flexible system. In this study the phantom of the synthetic breast-equivalent resin material for the process of the A/D conversion of mammograms was employed. The digital values can offset the difference in characteristics between the mammography system, the unit, etc. Furthermore the features of our system use the neural network, and then tune the neural network by the histogram of the digital values and by the radiologists' and expert mammographers' assessment ability. Although there was an observer's bias, our system was able to classify the breast density automatically according to that observer. This is only possible if the observer has been trained to some extent and is capable of maintaining an objective assessment according to the assessment criteria.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsZ. Guangjun, Z. Huijie, W. Zhongyu
Pages508-511
Number of pages4
Volume5253
DOIs
Publication statusPublished - 2003
EventFifth International Symposium on Instrumentation and Control Technology - Beijing, China
Duration: Oct 24 2003Oct 27 2003

Other

OtherFifth International Symposium on Instrumentation and Control Technology
CountryChina
CityBeijing
Period10/24/0310/27/03

Fingerprint

histograms
breast
Neural networks
Mammography
classifying
resins
Resins
X rays
x rays

Keywords

  • Breast density
  • Classification
  • Histogram

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Goto, S., Azuma, Y., Sumimoto, T., & Eiho, S. (2003). Classification of mammographic breast density by the histogram approach using neural networks. In Z. Guangjun, Z. Huijie, & W. Zhongyu (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5253, pp. 508-511) https://doi.org/10.1117/12.521828

Classification of mammographic breast density by the histogram approach using neural networks. / Goto, Sachiko; Azuma, Yoshiharu; Sumimoto, Tetsuhiro; Eiho, Shigeru.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / Z. Guangjun; Z. Huijie; W. Zhongyu. Vol. 5253 2003. p. 508-511.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Goto, S, Azuma, Y, Sumimoto, T & Eiho, S 2003, Classification of mammographic breast density by the histogram approach using neural networks. in Z Guangjun, Z Huijie & W Zhongyu (eds), Proceedings of SPIE - The International Society for Optical Engineering. vol. 5253, pp. 508-511, Fifth International Symposium on Instrumentation and Control Technology, Beijing, China, 10/24/03. https://doi.org/10.1117/12.521828
Goto S, Azuma Y, Sumimoto T, Eiho S. Classification of mammographic breast density by the histogram approach using neural networks. In Guangjun Z, Huijie Z, Zhongyu W, editors, Proceedings of SPIE - The International Society for Optical Engineering. Vol. 5253. 2003. p. 508-511 https://doi.org/10.1117/12.521828
Goto, Sachiko ; Azuma, Yoshiharu ; Sumimoto, Tetsuhiro ; Eiho, Shigeru. / Classification of mammographic breast density by the histogram approach using neural networks. Proceedings of SPIE - The International Society for Optical Engineering. editor / Z. Guangjun ; Z. Huijie ; W. Zhongyu. Vol. 5253 2003. pp. 508-511
@inproceedings{d01ef2ea24984b6b9eefc7036f9d5641,
title = "Classification of mammographic breast density by the histogram approach using neural networks",
abstract = "Our aim was to improve the accuracy of classifying x-ray mammographic breast densities. The histogram approach using the neural network was used for the purpose of constructing a flexible system. In this study the phantom of the synthetic breast-equivalent resin material for the process of the A/D conversion of mammograms was employed. The digital values can offset the difference in characteristics between the mammography system, the unit, etc. Furthermore the features of our system use the neural network, and then tune the neural network by the histogram of the digital values and by the radiologists' and expert mammographers' assessment ability. Although there was an observer's bias, our system was able to classify the breast density automatically according to that observer. This is only possible if the observer has been trained to some extent and is capable of maintaining an objective assessment according to the assessment criteria.",
keywords = "Breast density, Classification, Histogram",
author = "Sachiko Goto and Yoshiharu Azuma and Tetsuhiro Sumimoto and Shigeru Eiho",
year = "2003",
doi = "10.1117/12.521828",
language = "English",
volume = "5253",
pages = "508--511",
editor = "Z. Guangjun and Z. Huijie and W. Zhongyu",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Classification of mammographic breast density by the histogram approach using neural networks

AU - Goto, Sachiko

AU - Azuma, Yoshiharu

AU - Sumimoto, Tetsuhiro

AU - Eiho, Shigeru

PY - 2003

Y1 - 2003

N2 - Our aim was to improve the accuracy of classifying x-ray mammographic breast densities. The histogram approach using the neural network was used for the purpose of constructing a flexible system. In this study the phantom of the synthetic breast-equivalent resin material for the process of the A/D conversion of mammograms was employed. The digital values can offset the difference in characteristics between the mammography system, the unit, etc. Furthermore the features of our system use the neural network, and then tune the neural network by the histogram of the digital values and by the radiologists' and expert mammographers' assessment ability. Although there was an observer's bias, our system was able to classify the breast density automatically according to that observer. This is only possible if the observer has been trained to some extent and is capable of maintaining an objective assessment according to the assessment criteria.

AB - Our aim was to improve the accuracy of classifying x-ray mammographic breast densities. The histogram approach using the neural network was used for the purpose of constructing a flexible system. In this study the phantom of the synthetic breast-equivalent resin material for the process of the A/D conversion of mammograms was employed. The digital values can offset the difference in characteristics between the mammography system, the unit, etc. Furthermore the features of our system use the neural network, and then tune the neural network by the histogram of the digital values and by the radiologists' and expert mammographers' assessment ability. Although there was an observer's bias, our system was able to classify the breast density automatically according to that observer. This is only possible if the observer has been trained to some extent and is capable of maintaining an objective assessment according to the assessment criteria.

KW - Breast density

KW - Classification

KW - Histogram

UR - http://www.scopus.com/inward/record.url?scp=2342508526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2342508526&partnerID=8YFLogxK

U2 - 10.1117/12.521828

DO - 10.1117/12.521828

M3 - Conference contribution

VL - 5253

SP - 508

EP - 511

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

A2 - Guangjun, Z.

A2 - Huijie, Z.

A2 - Zhongyu, W.

ER -