Fuzzy based micro calcification segmentation

• Main Authors: Mohanalin, J., Kalra, P.K., Kumar, N.
• Format: Conference Proceeding
• Language: English
• Subjects: Biochemistry; Breast cancer; Cancer detection; Diagnostic radiography; Fuzzy logic; Image segmentation; Low pass filters; Mammography; Medical treatment; X-ray imaging
• DOI: 10.1109/ICECE.2008.4769171

Breast cancer is one of the leading causes of women death in the world. Since the causes are unknown, breast cancer cannot be prevented. Micro calcifications are the earliest signs of breast cancer and their detection is one of the most important research areas now. A novel approach for image segmentation of denser mammography images is introduced, for more accurate detection of microcalcifications clusters. In original mammographic images obtained by X-ray radiography, most of the information is hidden to the human observer. The fundamental idea of the proposed approach is to fuzzify the original image of a mammogram in order to make the difference between the backgrounds and object more. Then we enhance the region of interest and simultaneously suppress the tissues along with background thereby we do segmentation. The advantage of the proposed method is its ability to detect micro calcifications in very dense breast mammograms and also not to loose any vital data .Lot of clinical mammograms was used to test the fidelity of this algorithm. The experiments suggest that the micro calcifications are not only accurately detected but also enhance the visibility of micro calcifications.