A novel method of mass segmentation in mammogram

Author

Han, Zhen-zhong ; Chen, Hou-jin ; Li, Ju-peng ; Yao, Chang

Author_Institution

Sch. of Electron. & Inf. Eng., Beijing Jiaotong Univ., Beijing, China

fYear

2012

fDate

19-20 May 2012

Firstpage

1412

Lastpage

1416

Abstract

Mass detection in mammogram is one of effective technology for breast cancer diagnosis. A novel method of mass segmentation in mammogram is proposed in this paper. First, a mathematical model (MM) of the mass is presented to detect the location of mass. Second, based on the time series features generated by Pulse Coupled Neural Network (PCNN), the pixels are classified by Fuzzy C-Means clustering (FCM) algorithm. Last, combining the location and the cluster results, segmentation of masses can be achieved effectively. The experimental results show that mass detected by this method is accurate and the false positive (FP) rate is very low. The detection rate of masses reached 98.82%.

Keywords

cancer; fuzzy set theory; image segmentation; mammography; medical image processing; neural nets; pattern clustering; time series; FCM algorithm; PCNN; for breast cancer diagnosis; fuzzy c-means clustering algorithm; mammogram; mass detection; mass segmentation; mathematical model; pulse coupled neural network; time series features; Breast cancer; Classification algorithms; Clustering algorithms; Image segmentation; Mathematical model; Time series analysis; Breast cancer; FCM; Mammogram; Mass segmentation; Mathematical model; PCNN;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems and Informatics (ICSAI), 2012 International Conference on

Conference_Location

Yantai

Print_ISBN

978-1-4673-0198-5

Type

conf

DOI

10.1109/ICSAI.2012.6223300

Filename

6223300