Title :
A novel breast mass diagnosis system based on Zernike moments as shape and density descriptors
Author :
Tahmasbi, Amir ; Saki, Fatemeh ; Aghapanah, Hamed ; Shokouhi, Shahriar B.
Author_Institution :
Dept. of Electr. Eng., Univ. of Texas at Dallas, Richardson, TX, USA
Abstract :
In this paper, a novel Computer-aided Diagnosis (CADx) system has been proposed for mass diagnosis in mammography images. Zernike moments are utilized as descriptors of shape and density characteristics in order to improve the overall accuracy. The input Regions of Interest (ROI) are segmented and subjected to some preprocessing stages. The outcome of preprocessing stage is a gray-scale image containing co-scaled translated mass which contains both shape and density characteristics of the mass. Two groups of Zernike moments have been extracted from the preprocessed images. Considering the performance of the overall system the most effective moments have been chosen and applied to a Multi-layer Perceptron (MLP) classifier. The Receiver Operational Characteristics (ROC) plot and the performance of overall CADx system are analyzed for each group of features. The average achieved area under ROC curve (Az) and False Positive Rate (FPR) for high-order moments are 0.872 and 18.34%, respectively. Besides, for low-order moments those are equal to 0.824 and 15.44%, respectively.
Keywords :
image classification; image segmentation; mammography; medical image processing; multilayer perceptrons; CADx system; FPR; MLP classifier; ROC plot; Zernike moments; breast mass diagnosis system; computer aided diagnosis; coscaled translated mass; density descriptors; false positive rate; gray scale image; mammography images; multilayer perceptron classifier; preprocessing stages; receiver operational characteristic plot; regions of interest segmentation; shape descriptors; Accuracy; Biomedical engineering; Breast; Cancer; Computational complexity; Feature extraction; Shape; Computer aided diagnosis; Zernike moments; mammography; multi layer Perceptron;
Conference_Titel :
Biomedical Engineering (ICBME), 2011 18th Iranian Conference of
Conference_Location :
Tehran
Print_ISBN :
978-1-4673-1004-8
DOI :
10.1109/ICBME.2011.6168532
