A novel fuzzy logic approach to mammogram contrast enhancement

被引:62
作者
Cheng, HD [1 ]
Xu, HJ [1 ]
机构
[1] Utah State Univ, Dept Comp Sci, Logan, UT 84322 USA
关键词
D O I
10.1016/S0020-0255(02)00293-1
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Breast cancer continues to be a significant public health problem in the United States. Primary prevention seems impossible since the causes of this disease still remain unknown. Early detection is the key to improving breast cancer prognosis. Mammography has been one of the most reliable methods for early detection of breast carcinomas. However, it is difficult for radiologists to provide both accurate and uniform evaluation for the enormous number of mammograms generated in widespread screening. Automated breast cancer diagnosis attracts much attention of the researchers. However, the fuzzy nature of the mammograms and the low contrast between the breast cancer and its surroundings make the automated breast cancer detection very difficult. Mammogram. contrast enhancement is critical and essential to breast cancer diagnosis. This paper uses an adaptive fuzzy logic contrast enhancement method to enhance mammographic features. We first normalize the mammograms to reduce the effects of different illuminations. Then, we fuzzify the normalized images based on the maximum fuzzy entropy principle. The local contrast is measured and enhanced by utilizing both the global and local information so that the fine details of mammograms can be enhanced and the noise can be suppressed. The histogram of the mammogram provides the global information and the fuzzy entropy of local window is computed to analyze the local information. Then, we use both the global and local information to define and enhance the contrast. Finally, the defuzzification is performed to transform the enhanced mammograrn back to the spatial domain. The experiments demonstrate that the proposed method can effectively enhance the contours and fine details of the mamographic features which will be useful for breast cancer diagnosis. (C) 2002 Elsevier Science Inc. All rights reserved.
引用
收藏
页码:167 / 184
页数:18
相关论文
共 30 条
[1]  
Andersson I, 1987, Recent Results Cancer Res, V105, P62
[2]  
[Anonymous], 1998, PHYS A
[3]  
[Anonymous], HDB PATTERN RECOGNIT
[4]   CONTRAST ENHANCEMENT TECHNIQUE BASED ON LOCAL DETECTION OF EDGES [J].
BEGHDADI, A ;
LENEGRATE, A .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1989, 46 (02) :162-174
[5]   CANCER STATISTICS, 1994 [J].
BORING, CC ;
SQUIRES, TS ;
TONG, T ;
MONTGOMERY, S .
CA-A CANCER JOURNAL FOR CLINICIANS, 1994, 44 (01) :7-26
[6]   A novel approach to microcalcification detection using fuzzy logic technique [J].
Cheng, HD ;
Lui, YM ;
Freimanis, RI .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1998, 17 (03) :442-450
[7]   Thresholding using two-dimensional histogram and fuzzy entropy principle [J].
Cheng, HD ;
Chen, YH ;
Jiang, XH .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2000, 9 (04) :732-735
[8]   Threshold selection based on fuzzy c-partition entropy approach [J].
Cheng, HD ;
Chen, JR ;
Li, JG .
PATTERN RECOGNITION, 1998, 31 (07) :857-870
[9]   A novel fuzzy logic approach to contrast enhancement [J].
Cheng, HD ;
Xu, HJ .
PATTERN RECOGNITION, 2000, 33 (05) :809-819
[10]  
CHENG HD, 2001, FUZZY LOGIC MED