发明名称 |
METHOD FOR DETERMINING OPTIMALLY WEIGHTED WAVELET TRANSFORM |
摘要 |
A computer-aided diagnosis (CAD) method for detection of clustered microcalcifications in digital mammograms based on an image reconstruction using a substantially optimally weighted wavelet transform (4, 6 and 8). Weights at individual scales of the wavelet transform are optimized based on a supervised learning method (6). In the learning method, an error function (12) represents a difference between a desired output (14) and a reconstructed image (10) obtained from weighted wavelet coefficients of the wavelet transform for a given mammogram. The error function is then minimized by modifying the weights by means of a conjugate gradient algorithm. Performance of the optimally weighted wavelets was evaluated by means of receiver-operating characteristic (ROC) analysis which indicated that the present invention outperformed both a difference-image technique and partial reconstruction method currently used in CAD methods.
|
申请公布号 |
WO9928860(A1) |
申请公布日期 |
1999.06.10 |
申请号 |
WO1998US24933 |
申请日期 |
1998.11.25 |
申请人 |
ARCH DEVELOPMENT CORPORATION |
发明人 |
YOSHIDA, HIROYUKI;ZHANG, WEI;NISHIKAWA, ROBERT, M.;KUNIO, DOI |
分类号 |
G06F17/14;G06T7/00;(IPC1-7):G06K9/80 |
主分类号 |
G06F17/14 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|