Automatic segmentation of mammographic masses using fuzzy shadow and maximum-likelihood analysis

This study attempted to accurately segment tumors in mammograms. Although this task is considered to be a preprocessing step in a computer analysis program, it plays an important role for further analysis of breast lesions. The region of interest (ROI) was segmented using the pixel aggregation and region growing techniques combined with maximum likelihood analysis. A fast segmentation algorithm has been developed to facilitate the segmentation process. The algorithm repetitively sweeps the ROI horizontally and vertically to aggregate the pixels that have intensifies higher than a threshold. The ROI is then fuzzified by the Gaussian envelope. With each segmented region for a given threshold step in the original ROI, the likelihood function is computed and is comprised of probability density functions inside and outside of the fuzzified ROI. We have implemented this method to test on 90 mammograms. We found the segmented region with the maximum likelihood corresponds to the body of tumor. However, the segmented region with the maximum change of likelihood corresponds to the tumor and it extended margin.

[1]  L. Tabár,et al.  Teaching atlas of mammography. , 1983, Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin. Erganzungsband.

[2]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[3]  R A Clark,et al.  False-positive reduction in CAD mass detection using a competitive classification strategy. , 2001, Medical physics.

[4]  K. J. Ray Liu,et al.  Computerized radiographic mass detection. I. Lesion site selection by morphological enhancement and contextual segmentation , 2001, IEEE Transactions on Medical Imaging.

[5]  N. Obuchowski,et al.  Quantitative classification of breast tumors in digitized mammograms. , 1996, Medical physics.

[6]  Richard H. Moore,et al.  Current Status of the Digital Database for Screening Mammography , 1998, Digital Mammography / IWDM.

[7]  N. Karssemeijer,et al.  Segmentation of suspicious densities in digital mammograms. , 2001, Medical physics.

[8]  H P Chan,et al.  Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue. , 1996, Medical physics.

[9]  P. G. Tahoces,et al.  Computer-aided diagnosis: automatic detection of malignant masses in digitized mammograms. , 1998, Medical physics.

[10]  Maryellen L. Giger,et al.  Automated seeded lesion segmentation on digital mammograms , 1998, IEEE Transactions on Medical Imaging.

[11]  Berkman Sahiner,et al.  An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection , 1996, IEEE Trans. Medical Imaging.