Computerized Detection of Masses
in Digitized Mammograms Using
Single-Image Segmentation and a
Multilayer Topographic Feature
Analysis
Bin Zheng, PhD, Yuan-Hsiang Chang, MS, David Gur, ScD
Rationale and Objectives. We developed and evaluated a computer-
aided detection (CAD) scheme for masses in digitized mammograms.
Methods. A multistep CAD scheme was developed and tested. The
method uses a technique of single-image segmentation with Gaussian
bandpass filtering to yield a high sensitivity for mass detection. A rule-
based multilayer topographic feature analysis method is then used to clas-
sify suspected regions. A set of 260 cases, including 162 verified masses,
was divided into two subsets; one set was used to set the rule-based classi-
fication and one was used to test the performance of the scheme.
Results. In a preliminary clinical study, the implemented detection
scheme yielded 98% sensitivity with a false-positive detection rate of less
than one false-positive region per image.
Conclusion. Singleqmage segmentation methods seem to have high
sensitivity in selecting true-positive mass regions in the first stage of a CAD
scheme. A multilayer topographic image feature analysis method in the
second stage of a CAD scheme has the potential to significantly reduce the
false-positive detection rate.
Key Words. Mammography; computer-aided detection; digital mammo-
grams; mass detection; medical image processing.
From the Department of Radiology, University of
Pittsburgh, Pittsburgh, PA.
Address reprint requests to B. Zheng, PhD, Depart-
ment of Radiology, A449 Scaife Hall, University of
Pittsburgh, 3550 Terrace St., Pittsburgh, PA 15261-
0001.
Received April 13, 1995, and accepted for publica-
tion after revision July 21, 1995.
Acad Radio11995;2:959-966
© 1995, Association of University Radiologists
B
reast cancer is one of the leading causes of death in women over the
age of 40 [1]. There is ample evidence that early detection plays an
important role in reducing breast cancer morbidity and mortality [2, 3].
Many methods have been investigated to improve the early detection of
breast cancer, but mammography has proved to be the most cost-effective
means to provide useful information about the presence of abnormal tis-
sues, such as cancer, in the breast [4].
Because of the difficulty in interpreting mammograms, multiple readings
of a single examination are often desirable to increase the reliability of a
diagnosis [5]. Furthermore, because of the subtlety of certain breast abnor-
malities and the complexity of the reading task, mammographers may poten-
959