Title :
Spatial distribution modeling for detection of clustered microcalcifications
Author :
Jing, Hao ; Yang, Yongyi
Author_Institution :
Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA
Abstract :
We propose a spatial point-process modeling approach to improve the detection of clustered microcalcifications (MCs) in mammogram images. Apart from the predominant approach for MC detection, in which individual MCs in an image are first detected independently and then grouped into clusters, our proposed approach aims to incorporate the spatial clustering property of the MCs directly into the detection process (i.e., MCs tend to appear in small clusters). We model the MCs by a marked point process (MPP) in which spatially neighboring MCs are interactive with each other. The detection is achieved through maximum a posteriori (MAP) estimation of the parameters of the MPP model. The proposed approach was evaluated with a dataset of 141 clinical mammograms, and the results show that it could yield improved performance compared with a recently proposed SVM detector.
Keywords :
mammography; maximum likelihood estimation; medical image processing; pattern clustering; clustered microcalcification detection; mammogram images; marked point process; maximum a posteriori estimation; spatial clustering property; spatial distribution modeling; spatial point-process modeling approach; Breast cancer; Calcium; Cancer detection; Clustering algorithms; Detectors; Lesions; Object detection; Parameter estimation; Support vector machine classification; Support vector machines; Clustered microcalcifications; computer-aided detection; marked point process; spatial point process;
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2009.5414063