Automatic cropping of breast regions for registration in MR mammography

Matthias Koenig; Sven Kohle; Heinz-Otto Peitgen

doi:10.1117/12.594522

29 April 2005 Automatic cropping of breast regions for registration in MR mammography

Matthias Koenig, Sven Kohle, Heinz-Otto Peitgen

Proceedings Volume 5747, Medical Imaging 2005: Image Processing; (2005) https://doi.org/10.1117/12.594522
Event: Medical Imaging, 2005, San Diego, California, United States

Abstract

In MR mammography, usually the complete upper part of the body is recorded although for most diagnostic examinations and therapeutic planning only the regions around the breasts are important. This can lead to some disadvantages for automatic processing of images, e.g. higher time consumption and lesser accuracy in image registration. In this paper, we present a straight-forward method for automatic cropping of breast regions for registration in MR mammography. The method starts with processing two-dimensional slices. The result of this first step is statistically analyzed and a cropping-region for three-dimensional volumes is calculated. For each two-dimensional slice, the boundary between breast and air is identified by applying a threshold operator. This boundary describes a bimodal curve; the peaks for the right and left breast and the breastbone are found by searching among the curve's extremal points. An heuristic method analyzes this curve and further yields an estimation of the chest wall boundary to the inner body. For image registration purpose, we compare our proposed automatic cropping method with a simple cropping mechanism that defines the regions of the left and right breasts by reducing the volume to 60 percent from the margin of each side. It is shown that the proposed method works reliably and gives advantages regarding the time-quality tradeoff for automatic image registration in MR mammography.

Citation Download Citation

Matthias Koenig, Sven Kohle, and Heinz-Otto Peitgen "Automatic cropping of breast regions for registration in MR mammography", Proc. SPIE 5747, Medical Imaging 2005: Image Processing, (29 April 2005); https://doi.org/10.1117/12.594522

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