Cancerous tumor mass is one of the major types of breast cancer. When cance
rous masses are embedded in and camouflaged by varying densities of parench
ymal tissue structures, they are very difficult to be visually detected on
mammograms. This paper presents an algorithm that combines several artifici
al intelligent techniques with the discrete wavelet transform (DWT) for det
ection of masses in mammograms. The AI techniques include fractal dimension
analysis, multiresolution markov random field, dogs-and-rabbits algorithm,
and others. The fractal dimension analysis serves as a preprocessor to det
ermine the approximate locations of the regions suspicious for cancer in th
e mammogram, The dogs-and-rabbits clustering algorithm is used to initiate
the segmentation at the LL subband of a three-level DWT decomposition of th
e mammogram. A tree-type classification strategy is applied at the end to d
etermine whether a given region is suspicious for cancer. We have verified
the algorithm with 322 mammograms in the Mammographic Image Analysis Societ
y Database. The verification results show that the proposed algorithm has a
sensitivity of 97.3% and the number of false positive per image is 3.92.