Open AccessStatistical Texture Model for mass Detection in Mammography
Author(s) -
Nicolás Gallego-Ortiz,
David S. Fernández-McCann
Publication year - 2013
Publication title -
revista de ingeniería
Language(s) - English
Resource type - Journals
eISSN - 2011-0049
pISSN - 0121-4993
DOI - 10.16924/revinge.39.2
Subject(s) - artificial intelligence , mammography , computer science , pixel , pattern recognition (psychology) , context (archaeology) , computer vision , texture (cosmology) , mixture model , visualization , image texture , statistical model , segmentation , feature (linguistics) , gaussian , probabilistic logic , multivariate normal distribution , multivariate statistics , image segmentation , image (mathematics) , machine learning , medicine , geography , physics , cancer , archaeology , linguistics , quantum mechanics , breast cancer , philosophy
In the context of image processing algorithms for mass detection in mammography, texture is a key feature to be used to distinguish abnormal tissue from normal tissue. Recently, a texture model based on a multivariate gaussian mixture was proposed, of which the parameters are lear-ned in an unsupervised way from the pixel intensities of images. The model produces images that are probabilistic maps of texture normality and it was proposed as a visua-lization aid for diagnostic by clinical experts. In this paper, the usability of the model is studied for automatic mass de-tection. A segmentation strategy is proposed and evaluated using 79 mammography cases.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom