Radon-domain detection of the nipple and the pectoral muscle in mammograms

被引:50
作者
Kinoshita, S. K. [1 ,2 ]
Azevedo-Marques, P. M. [1 ]
Pereira, R. R., Jr. [1 ]
Rodrigues, J. A. H. [1 ]
Rangayyan, R. M. [3 ,4 ]
机构
[1] Univ Sao Paulo, Fac Med Ribeirao Preto, Image Sci & med Phys Ctr, Dept Internal Med, BR-14048900 Ribeirao Preto, SP, Brazil
[2] Univ Sao Paulo, Dept Elect Engn, BR-14048900 Ribeirao Preto, SP, Brazil
[3] Univ Calgary, Schulich Sch Engn, Dept Elect & Comp Engn, Calgary, AB T2N 1N4, Canada
[4] Univ Calgary, Dept Radiol, Calgary, AB T2N 1N4, Canada
基金
巴西圣保罗研究基金会;
关键词
digital mammography; nipple detection; pectoral muscle detection; radon transform; image processing;
D O I
10.1007/s10278-007-9035-6
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
In this paper, methods are presented for automatic detection of the nipple and the pectoral muscle edge in mammograms via image processing in the Radon domain. Radon-domain information was used for the detection of straight-line candidates with high gradient. The longest straight-line candidate was used to identify the pectoral muscle edge. The nipple was detected as the convergence point of breast tissue components, indicated by the largest response in the Radon domain. Percentages of false-positive (FP) and false-negative (FN) areas were determined by comparing the areas of the pectoral muscle regions delimited manually by a radiologist and by the proposed method applied to 540 mediolateral-oblique (MLO) mammographic images. The average FP and FN were 8.99% and 9.13%, respectively. In the detection of the nipple, an average error of 7.4 mm was obtained with reference to the nipple as identified by a radiologist on 1,080 mammographic images (540 MLO and 540 craniocaudal views).
引用
收藏
页码:37 / 49
页数:13
相关论文
共 30 条
[1]  
[Anonymous], BIOMEDICAL IMAGE ANA
[2]  
[Anonymous], IEEE T SYST MAN CYBE
[3]   Calculating the Hausdorff distance between curves [J].
Belogay, E ;
Cabrelli, C ;
Molter, U ;
Shonkwiler, R .
INFORMATION PROCESSING LETTERS, 1997, 64 (01) :17-22
[5]   IMAGE SELECTIVE SMOOTHING AND EDGE-DETECTION BY NONLINEAR DIFFUSION [J].
CATTE, F ;
LIONS, PL ;
MOREL, JM ;
COLL, T .
SIAM JOURNAL ON NUMERICAL ANALYSIS, 1992, 29 (01) :182-193
[6]  
CATTE F, 1992, SIAM J NUMER ANAL, V29, P845
[7]   A simple method for automatically locating the nipple on mammograms [J].
Chandrasekhar, R ;
Attikiouzel, Y .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1997, 16 (05) :483-494
[8]   Automatic identification of the pectoral muscle in mammograms [J].
Ferrari, RJ ;
Rangayyan, RM ;
Desautels, JEL ;
Borges, RA ;
Frère, AF .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2004, 23 (02) :232-245
[9]   Analysis of asymmetry in mammograms via directional filtering with Gabor wavelets [J].
Ferrari, RJ ;
Rangayyan, RM ;
Desautels, JEL ;
Frère, AF .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (09) :953-964
[10]  
Gonzalez R.C., 2007, DIGITAL IMAGE PROCES, V3rd