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

Sachiko Goto; Yoshiharu Azuma; Tetsuhiro Sumimoto; Shigeru Eiho

doi:10.1117/12.521828

2 September 2003 Classification of mammographic breast density by the histogram approach using neural networks

Sachiko Goto, Yoshiharu Azuma, Tetsuhiro Sumimoto, Shigeru Eiho

Proceedings Volume 5253, Fifth International Symposium on Instrumentation and Control Technology; (2003) https://doi.org/10.1117/12.521828
Event: Fifth International Symposium on Instrumentation and Control Technology, 2003, Beijing, China

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.

Citation Download Citation

Sachiko Goto, Yoshiharu Azuma, Tetsuhiro Sumimoto, and Shigeru Eiho "Classification of mammographic breast density by the histogram approach using neural networks", Proc. SPIE 5253, Fifth International Symposium on Instrumentation and Control Technology, (2 September 2003); https://doi.org/10.1117/12.521828

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available