Introduction:  Breast  cancer  is  a  leading  cause  of  death  among  females  throughout  the  world.  Currently, 
radiologists are able to detect only 75% of breast cancer cases. Making use of computer-aided design (CAD) 
can play an important role in helping radiologists perform more accurate diagnoses.  
Material and Methods: Using our hybrid method, the background and the pectoral muscle were removed 
from mammography images and image contrast was enhanced using an adaptive density weighted method. 
First,  suspected  regions  were  extracted  based  on  mathematical  morphology  and  adaptive  thresholding 
approaches. Then, in order to reduce the false positives in the suspected regions obtained in the first stage, the 
corresponding features were extracted using a wavelet transform, followed by the application of a support 
vector machine to detect masses.  
Results: A Mammographic Image Analysis Society (MIAS) database was used to evaluate the performance 
of  the  algorithm.  The  sensitivity  of  81%  and  specificity  of  84%  were  achieved  in  detecting  masses. 
Improvement  of  sensitivity  and  specificity  with  our  proposed  hybrid  algorithm  was  demonstrated  by 
subjective  expert-based  and  objective  ROC-based  techniques  in  comparison  with  the  currently  acceptable 
method by Masotti. 
Disscusion and Conclusion: In this paper, a hybrid method of pixel-based and region-based mass detection 
approaches is proposed to increase the specificity of the results. The accessory stage (using wavelet features) 
increased the sensitivity by 30%. It can be concluded that the proposed algorithm is an efficient and robust 
method for different types of mass detection in low-quality mammography images.