Title :
Surrounding region dependence method for detection of clustered microcalcifications on mammograms
Author :
Jong Kook Kim ; Hyun Wook Park
Author_Institution :
Dept. of Inf. & Commun. Eng., Korea Adv. Inst. of Sci. & Technol., Seoul
Abstract :
Clustered microcalcifications on X-ray mammograms are an important feature in the detection of breast cancer. For the detection of the clustered microcalcification on digitized mammograms, this paper proposes a texture analysis method called the surrounding region dependence method (SRDM), which is a statistical texture analysis based on the second-order histogram in two surrounding regions. Four textural features are extracted from the SRDM. These features are used to classify region of interests (ROIs) into positive ROIs containing clustered microcalcifications and negative ROIs of normal breast tissues. The three-layer backpropagation neural network is employed as a classifier with input data of four textural features. The classification performance of the proposed method is evaluated by using the round-robin method and the receiver operating-characteristics (ROC) analysis
Keywords :
backpropagation; diagnostic radiography; feature extraction; image classification; image segmentation; image texture; medical image processing; multilayer perceptrons; statistical analysis; X-ray mammograms; breast cancer; classification performance; clustered microcalcifications detection; digitized mammograms; feature extraction; normal breast tissues; receiver operating-characteristics; region of interests classification; round-robin method; second-order histogram; statistical texture analysis; surrounding region dependence method; texture analysis method; three-layer backpropagation neural network; Backpropagation; Breast cancer; Breast tissue; Cancer detection; Computer vision; Data mining; Feature extraction; Histograms; X-ray detection; X-ray detectors;
Conference_Titel :
Image Processing, 1997. Proceedings., International Conference on
Conference_Location :
Santa Barbara, CA
Print_ISBN :
0-8186-8183-7
DOI :
10.1109/ICIP.1997.635642