Title :
Analysis of mammographic microcalcifications using a computationally efficient filter bank
Author :
Gulsrud, Thor Ole
Author_Institution :
Dept. of Electr. & Comput. Eng., Stavanger Univ. Coll., Norway
Abstract :
We present a new method for classification of malignant and benign clusters of microcalcifications in digital mammograms. A computationally efficient infinite impulse response (IIR) quadrature mirror filter (QMF) bank is used as a tool for extracting texture and shape features. The filter bank splits the input image into four subbands: low-low band, low-high band, high-low band and high-high band. Texture and shape features based on cooccurrence matrices are computed from the subsampled subbands. The low-low band extracts the information of spatial dependence and the higher frequency bands extract the shape information. The results of an experimental study demonstrate that our approach drastically improves the overall performance compared to a manual system
Keywords :
IIR filters; cancer; channel bank filters; diagnostic radiography; feature extraction; image texture; mammography; matrix algebra; medical image processing; quadrature mirror filters; tumours; IIR filter; breast cancer; computer-aided diagnosis; cooccurrence matrices; digital mammograms; infinite impulse response filter; mammographic microcalcifications; mammography; multichannel filtering; quadrature mirror filter bank; shape feature extraction; statistical descriptors; texture feature extraction; Breast biopsy; Breast cancer; Data mining; Educational institutions; Filter bank; Frequency; IIR filters; Image databases; Mirrors; Shape;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on
Conference_Location :
Salt Lake City, UT
Print_ISBN :
0-7803-7041-4
DOI :
10.1109/ICASSP.2001.941341
