Mass Segmentation In Mammograms Research Articles

Breast mass segmentation using region-based and edge-based methods in a 4-stage multiscale system

Mass segmentation in mammograms is a challenging task due to problems such as low contrast, ill-defined, fuzzy or spiculated borders, and the presence of intensity inhomogeneities. These facts complicate the development of computer-aided diagnosis (CAD) systems to assist radiologists. In this paper, a novel mass segmentation algorithm for mammograms based on robust multiscale feature-fusion, and automatic estimation based maximum a posteriori (MAP) method is presented. The proposed segmentation technique consists of mainly four stages: a dynamic contrast improvement scheme applied to a selected region-of-interest (ROI), background-influence correction by template matching, detection of mass candidate points by prior and posterior probabilities based on robust multiscale feature-fusion, and final delineation of the mass region by a MAP scheme. This segmentation method is applied to 480 ROI masses that used ground truth from two radiologists. To compare its effectiveness with the state-of-the-art segmentation methods, three statistical metrics are employed. The experimental results indicate that the developed methods can reliably segment ill-defined or spiculated lesions when compared to other algorithms. Its integration in a CAD system may result in an improved aid to radiologists.

Toward breast cancer diagnosis based on automated segmentation of masses in mammograms

This work explores the use of characterization features extracted based on breast-mass contours obtained by automated segmentation methods, for the classification of masses in mammograms according to their diagnosis (benign or malignant). Two sets of mass contours were obtained via two segmentation methods (a dynamic-programming-based method and a constrained region-growing method), and simplified versions of these contours (modeling the contours as ellipses) were employed to extract a set of six features designed for characterization of mass margins (contrast between foreground region and background region, coefficient of variation of edge strength, two measures of the fuzziness of mass margins, a measure of spiculation based on relative gradient orientation, and a measure of spiculation based on edge-signature information). Three popular classifiers (Bayesian classifier, Fisher's linear discriminant, and a support vector machine) were then used to predict the diagnosis of a set of 349 masses based on each of said features and some combinations of these. The systems (each system consists of a segmentation method, a featureset, and a classifier) were compared with each other in terms of their performance on the diagnosis of the set of breast masses. It was found that, although there was a percent difference of about 14% in the average segmentation quality between methods, this was translated into an average percent difference of only 4% in the classification performance. It was also observed that the spiculation feature based on edge-signature information was distinctly better than the rest of the features, although it is not very robust to changes in the quality of the segmentation. All systems were more efficient in predicting the diagnosis of benign masses than that of the malignant masses, resulting in low sensitivity and high specificity values (e.g. 0.6 and 0.8, respectively) since the positive class in the classification experiments is the set of malignant masses. It was concluded that features extracted from automated contours can contribute to the diagnosis of breast masses in screening programs by correctly identifying a majority of benign masses.

Improved dynamic‐programming‐based algorithms for segmentation of masses in mammograms

In this paper, two new boundary tracing algorithms for segmentation of breast masses are presented. These new algorithms are based on the dynamic programming-based boundary tracing (DPBT) algorithm proposed in Timp and Karssemeijer, [S. Timp and N. Karssemeijer, Med. Phys. 31, 958-971 (2004)] The DPBT algorithm contains two main steps: (1) construction of a local cost function, and (2) application of dynamic programming to the selection of the optimal boundary based on the local cost function. The validity of some assumptions used in the design of the DPBT algorithm is tested in this paper using a set of 349 mammographic images. Based on the results of the tests, modifications to the computation of the local cost function have been designed and have resulted in the Improved-DPBT (IDPBT) algorithm. A procedure for the dynamic selection of the strength of the components of the local cost function is presented that makes these parameters independent of the image dataset. Incorporation of this dynamic selection procedure has produced another new algorithm which we have called ID2PBT. Methods for the determination of some other parameters of the DPBT algorithm that were not covered in the original paper are presented as well. The merits of the new IDPBT and ID2PBT algorithms are demonstrated experimentally by comparison against the DPBT algorithm. The segmentation results are evaluated with base on the area overlap measure and other segmentation metrics. Both of the new algorithms outperform the original DPBT; the improvements in the algorithms performance are more noticeable around the values of the segmentation metrics corresponding to the highest segmentation accuracy, i.e., the new algorithms produce more optimally segmented regions, rather than a pronounced increase in the average quality of all the segmented regions.