Title :
Ipsilateral multi-view CAD system for mass detection in digital mammography
Author :
Sun, Xuejun ; Qian, Wei ; Song, Dansheng ; Robert, A.C.
Author_Institution :
Dept. of Interdisciplinary Oncology, Univ. of South Florida, FL, USA
Abstract :
An ipsilateral multi-view computer-aided diagnosis (CAD) scheme is presented for the earlier mass detection in digital mammograms. Tree structured nonlinear filtering (TSF) is used in image noise suppression. Two wavelet-based methods, directional wavelet transform (DWT) and tree structured wavelet transform (TSWT) are employed for image enhancement. Adaptive fuzzy-C means (FCM) algorithm is conducted for segmentation. Concurrent analysis is employed for iterative analysis of ipsilateral multi-view mammograms to raise detection sensitivity and specificity, and a supervised three-layer artificial neural network (ANN) in which the backpropagation (BP) algorithm combined with Kalman filtering is used as training algorithm is developed as a classifier, which has been trained using the training database with biopsy proven truth files. The application of such CAD system in digital mammography is reported in this article. The test database consists of 200 cases in which the distribution of normal, abnormal cases balanced, and free-response receiver operating characteristic (FROC) analysis method is used to test the performance of the developed unilateral CAD system. The performance comparison has been conducted between the final ipsilateral mufti-view CAD system and current single-view CAD system. The study results have shown that the advantages of ipsilateral mufti-view CAD method over current single-view CAD system express the feasibility of ipsilateral multi-view CAD system combined with concurrent analysis method described in this paper for the improvement of overall performance of CAD system in the early stage mass detection
Keywords :
Kalman filters; backpropagation; cancer; curve fitting; feature extraction; image classification; image enhancement; image segmentation; iterative methods; mammography; medical image processing; multilayer perceptrons; nonlinear filters; wavelet transforms; Kalman filtering; adaptive fuzzy-C means algorithm; artifact removal; backpropagation algorithm; biopsy proven truth files; breast cancer; computer-aided diagnosis scheme; concurrent analysis; database configuration; detection sensitivity; detection specificity; digital mammograms; directional wavelet transform; earlier mass detection; feature extraction; free-response receiver operating characteristic analysis; image classification; image decomposition; image enhancement; image noise suppression; image segmentation; ipsilateral multiview system; iterative analysis; performance comparison; supervised three-layer ANN; training algorithm; tree structured nonlinear filtering; tree structured wavelet transform; Algorithm design and analysis; Artificial neural networks; Backpropagation algorithms; Computer aided diagnosis; Databases; Filtering algorithms; Iterative algorithms; Performance analysis; System testing; Wavelet transforms;
Conference_Titel :
Mathematical Methods in Biomedical Image Analysis, 2001. MMBIA 2001. IEEE Workshop on
Conference_Location :
Kauai, HI
Print_ISBN :
0-7695-1336-0
DOI :
10.1109/MMBIA.2001.991695
