Using Priority Order of Basic Features for Circumscribed Masses Detection in Mammograms

摘要：

　　In this paper,we present a new technique for circumscribed masses detection in mammograms.Our method was implemented on mammographic images of masses from the Mini-MIAS database.A sensitivity of 95%was observed with only about 0.4 false alarms per image.To achieve above results,we carry out a progression with three main steps: Firstly,the input images have preprocessed with the aim to enhance key information of circumscribed masses; Secondly,we calculated and evaluated statistically basic features of abnormal regions on training database; Thirdly,mammograms on testing database were divided into equal blocks which calculated corresponding features; Finally,using priority order of basic features to classify blocks as an abnormal or normal regions.

关键词： mammograms circumscribed masses statistical evaluation preprocessing block priority order of basic features classify

作者: Le Minh Dong Yu Tsao Nguyen Viet Dung Sheng-Yu Peng Truong Quang Doan

作者单位: Department of Biomedical Engineering Hanoi University of Science and Technology,Vietnam Research Center for Information Technology Innovation,Academia Sinica,Taipei,Taiwan Department of Electrical Engineering National Taiwan University of Science and Technology,Taiwan

会议类型: 国际会议

会议名称: The 2014 ICME International Conference on Complex Medical Engineering (CME2014)ICME复合医学工程国际会议

会议地点: 台北

会议语种:英文

页码: 363-366,165

在线出版日期: 2014-06-26（万方平台首次上网日期，不代表论文的发表时间）