Accession Number : ADA314289

Title :   Wavelet Representation for Digital Mammography.

Descriptive Note : Annual rept. 16 Nov 94-15 Nov 95,

Corporate Author : FLORIDA UNIV GAINESVILLE

Personal Author(s) : Laine, Andrew F.

PDF Url : ADA314289

Report Date : DEC 1995

Pagination or Media Count : 131

Abstract : This report describes significant progress in the development of a methodology for accomplishing adaptive contrast enhancement by multiscale representations. Our studies have demonstrated that features extracted from multiresolution representations can provide an adaptive mechanism for the local emphasis of salient and subtle features of importance to mammography. We show that subtle features characteristic of mammographic findings required a finer parameterization of scale space than provided by traditional methods of wavelet analysis carried out at dyadic scales. The improved contrast of mammographic features make these techniques appealing for computed aided diagnosis (CAD) and screening mammography. Screening mammography examinations are certain to grow substantially in the next few years, and analytic methods that can assist general radiologists in reading mammograms shall be of great importance.

Descriptors :   *BREAST CANCER, *MAMMOGRAPHY, DATA BASES, ALGORITHMS, IMAGE PROCESSING, DIGITAL SYSTEMS, TISSUES(BIOLOGY), NEOPLASMS, DIAGNOSIS(MEDICINE), ADAPTIVE SYSTEMS, PATTERN RECOGNITION, NUMERICAL METHODS AND PROCEDURES, RADIOGRAPHY, BIOMEDICINE, CALCIFICATION, RADIOLOGY, HEALTH PHYSICS, CUBIC SPLINE TECHNIQUE, RADIOGRAPHIC FILM.

Subject Categories : Medicine and Medical Research
      Numerical Mathematics
      Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE