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

Sachiko Goto, Yoshiharu Azuma, Tetsuhiro Sumimoto, Shigeru Eiho

Research output: Contribution to journalConference articlepeer-review


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
Pages (from-to)508-511
Number of pages4
JournalProceedings of SPIE - The International Society for Optical Engineering
Publication statusPublished - Dec 1 2003
EventFifth International Symposium on Instrumentation and Control Technology - Beijing, China
Duration: Oct 24 2003Oct 27 2003


  • Breast density
  • Classification
  • Histogram

ASJC Scopus subject areas

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


Dive into the research topics of 'Classification of mammographic breast density by the histogram approach using neural networks'. Together they form a unique fingerprint.

Cite this