An application to processing mammogram images

Craig Henderson

May 2008


WinMammo Screenshot

WinMammo is the tangible result of my research. Written in C++, this windows application provides an interactive test bed for applying image processing and mammographic analysis algorithms to individual mammograms, or bilateral pairs.

Breast Orientation

When comparing mammogram images, whether temporal or bilateral, it is essential that the orientation of the breasts in each image match. This initial image orientation problem is generally omitted from the registration procedure and left to the operator to provide the x-ray images in the order and orientation that the software system requires. In a fully automated system, this is an unacceptable burden on the system operator.


Image segmentation describes a process in which an image is decomposed into smaller, significant constituent parts known as segmented objects. Hierarchical segmentation is an iterative procedure that recursively decomposes an image into ever smaller and significant objects. The accurate segmentation of a mammogram to identify the breast area is an important pre-processing step in mammogram analysis [1], and a two-phase segmentation is a common approach. The image is initially segmented to isolate the breast area from the background, and this area is then further segmented into regions of interest for analysis.

Global segmentation

WinMammo Screenshot Global segmentation is applied to the entire image and is used to separate the breast region from the non-breast (background) region. The background generally consists of a film label to identify the image, noise and other artefacts such as scratches or unexposed areas of film. Segmentation of these two regions will occur along the breast boundary, also known as the breast contour or skin-air interface. This boundary contains significant information relating to the deformation between two contralateral mammograms and is the source of information for relating the position of the nipple relative to the skin [2]. Accurate segmentation of this boundary is therefore important in bilateral comparisons as it identifies the region used in the registration of the images. The non-uniform deformation of the breast during the acquisition of a mediolateral oblique mammogram yields a weaker contrast along the breast boundary at the axilla. This region is the area where compression is reduced due to the closer proximity to the rigid chest wall. The contour on the mammogram image in this region will fade and the boundary of the breast may not be visible at all.

The simplest technique for achieving global segmentation of an image is thresholding. The intensity of each pixel in the image is compared to a predefined threshold value, and set to zero intensity (black) if it is lower, or full intensity (white) if it is greater. Global thresholding alone is inadequate for obtaining accurate skin boundary segmentation, however, because background noise appears at similar grey scale intensities as subcutaneous tissue.

Local segmentation

Local segmentation is used to delineate regions contained within the breast area such as the pectoral muscle and fibroglandular tissue (FGT) and fatty tissue.

Pectoral muscle segmentation

The pectoral muscle, pectoralis major or simply pectoralis, is seen in a mediolateral oblique (MLO) mammogram image as a triangular area in the top corner of a mediolateral oblique image. The edge should be visible to the level of the nipple and should appear slightly convex. The pectoralis minor is also shown in some MLO mammograms [3] and appears as a very bright triangular region in the top corner of the pectoralis major region. The presence of a pectoralis minor can complicate the algorithm to segment the pectoral muscle, as the mammogram appears to have two definable pectoral muscle candidates, and the algorithm must detect and select the most appropriate. In a craniocaudal (CC) images, the pectoralis major can be seen as a crescent of increased intensity on the vertical edge, but is generally visible in only 30-40% of images [3]. The pectoralis minor is not seen in CC mammograms.

Texture segmentation

There are three modes of analysis of a mammogram for detecting abnormality indicators: breast background texture, linear image structures such as spicules, vessels and ducts, and two-dimensional structures such as masses and microcalcifications. Note texture analysis of breast tissue regions as they are presented in the image can be sensitive to noise and natural variation in breast tissue structure.

Identification of the FGT region is also important as this region contains the ductal paths which are associated with high incidence of cancer. Once identified, mammographic parenchyma tissue can be classified into a number of grades, such as those proposed by Wolfe [4], that are used by radiologists for the assessment of risk in mammographic images [5]. In a 1998 paper, Bakic et al. [6] claims that as much as 99% of all breast cancers originate in the ductal networks. Indicators can be shown as microcalcifications within, or surrounding the ducts, or in bilateral asymmetric duct sizes that can show signs of disease.

Mammogram Registration

In obtaining a mammogram image, the breast is compressed between two plates parallel to the image plane. Registration of two mammograms taken of the same breast at different times (a temporal pair) [7] or of a left and right breast of a subject taken at the same time (a bilateral pair) [8] must account for two-dimensional projections of three-dimensional deformations which occur largely due to changes in position and pressure applied to the breast during the procedure [9]. It is therefore difficult to remove deformations that have caused changes in the 3D relationship of anatomical tissue structures [10].

Registration of segmented mammogram images first requires the identification of reference points in each of the images, either contralateral or temporal. The nipple is the only external anatomical feature of the breast, therefore locating its position is important to provide a specific reference point. However, the procedure is difficult, and good techniques are scarce in the literature. Ideally, the nipple will be in profile in an MLO image [3], however, it may not be visible at all, or it may be rotated into an unusual orientation as a consequence of the deformable non-rigid nature of the breast.

In corresponding bilateral images of deformable objects, such as mammograms, referencing the features can prove difficult because of the intrinsic nonlinear movement of internal structures. This movement is sensitive to the positioning of the patient and the pressure applied externally to the breast. The movement is nonlinear as the deformability of the breast is greater at the nipple than at the point of connectivity to the torso at the axilla and the rib cage. Georgsson has derived a dynamic referencing system that he calls anatomic coordinates that can be used to reference features within the deformable breast area. The coordinate system is dynamically positioned relative to a straight line approximation of the pectoral muscle, and it's perpendicular. Measurements can be recorded within this coordinate system to accurately position features of the breast tissue without any geometrical transformations of the image. [11]


[1] Wirth, M., Wang, R. and Lyon, J., 2003, Segmentation of high-intensity artifacts from mammograms using morphological reconstruction , University of Guelph.
[2] Wirth, M. and Stapinski, A., 2003, Segmentation of the breast region in mammograms using active contours , Visual Communications and Image Processing 5150 2006 pages.
[3] Cardenosa, G., 2001, Breast Imaging Companion , Lippincott Williams & Wilkins, 495 pages.
[4] Wolfe, J.N., 1976, Risk for breast cancer development determined by mammographic parenchymal pattern , Cancer 37 (5), pp. 2486-2492.
[5] Zwiggelaar, R., 1999, Separating Background Texture and Image Structure in Mammograms.
[6] Bakic, P., Brzakovic, D., Brzakovic, P. and Zhu, Z., 1998, An Approach to Using a Generalized Breast Model to Segment Digital Mammograms , Proc 11th IEEE Symp Computer-Based Medical Systems, Lubbock, TX..
[7] Kok-Wiles, S., Brady, J. and Highnam, R., 1998, Comparing Mammogram Pairs for the Detection of Lesions , 4th International Workshop on Digital Mammography (IWDM).
[8] Georgsson, F., 2003, Anatomical Coordinate System for Bilateral Registration of Mammograms , Lecture Notes in Computer Science 2749 (1), pp. 335-342.
[9] Wirth, M., Choi, C. and Jennings, A., 1999, A Nonrigid-Body Approach To Matching Mammograms, IEE Image Processing and its Applications 487 pages.
[10] Wirth, M., Narhan, J. and Gray, D., 2002, Non rigid mammogram registration using mutual information, Proceedings of SPIE Medical Imaging: Image Processing 4684, 573 pages.
[11] Georgsson, F., 2003, Anatomical Coordinate System for Bilateral Registration of Mammograms, Lecture Notes in Computer Science 2749 (1), pp. 335-342.