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

L. Kinnard1,2, S.-C.B. Lo1, P. Wang3, M.T. Freedman1, M. Chouikha2
1ISIS Center, Department of Radiology, Georgetown University Medical Center, Washington D.C., DC, USA
2Department of Electrical Engineering, Howard University College of Medicine, Washington D.C., DC, USA
3Biomedical NMR Laboratory, Department of Radiology, Howard University College of Medicine, Washington D.C., DC, USA

Tóm tắt

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.

Từ khóa

#Cancer #Image databases #Radiology #Breast neoplasms #Testing #Image segmentation #Intersymbol interference #Lesions #Benign tumors #Pixel

Tài liệu tham khảo

gonzalez, 1992 kupinski, 1998, Automated Seeded Lesion Segmentation on Digital Mammograms, IEEE Transactions on Medical Imaging, 17, 510 sahiner, 1996, Goodsit MM, Image feature selection by a genetic algorithm: Application to classification of mass and normal breast tissue, Medical Physics, 23, 1671 li, 2001, False-positive reduction in CAD mass detection using a competitive classification strategy, Medical Physics, 28, 250 10.1007/978-1-4899-3216-7 li, 2001, Computerized Radiographic Mass Detection – Part I Lesion Site Selection by Morphological Enhancement and Contextual Segmentation IEEE Transactions on Medical Imaging, 20, 289 tabar, 1983, Teaching Atlas of Mammography 10.1109/42.481441 10.1118/1.598274 heath, 1998, Current status of the Digital Database for Screening Mammography, Digital Mammography, 457, 10.1007/978-94-011-5318-8_75 10.1118/1.597707 gmte, 2001, Segmentation of suspicious densities in digital mammograms Medical Physics, 28, 259