DocumentCode
3089615
Title
Towards Computer-Aided Diagnostics of Screening Mammography Using Content-Based Image Retrieval
Author
Deserno, Thomas M. ; Soiron, Michael ; de Oliveira, J.E.E. ; de A Araujo, Arnaldo
Author_Institution
Dept. of Med. Inf., RWTH Aachen Univ., Aachen, Germany
fYear
2011
fDate
28-31 Aug. 2011
Firstpage
211
Lastpage
219
Abstract
Screening mammography has been established worldwide for early detection of breast cancer, one of the main causes of death among women in occidental countries. In this paper, we aim at moving towards computer-aided diagnostics of screening mammography. Tissue and lesion are classified using the methodology of content-based image retrieval. In addition, we aim at comprehensive evaluation and have established a large database of annotated reference images (ground truth), which has been merged and unified from different sources publicly available to research. In total, 10,509 mammographic images have been collected from the different sources. From this, 3,375 images are provided with one and 430 radiographs with more than one chain code annotations. This data supports experiments with up to 12 classes, and 233 images per class if a equal distribution is required. Using a two-dimensional principal component analysis with four eigenvalues and a support vector machine with Gaussian kernel for feature extraction and image retrieval, respectively, the precision of computer-aided diagnosis is above 80%. It therefore may be used as second opinion in screening mammography.
Keywords
Gaussian processes; biological tissues; cancer; content-based retrieval; eigenvalues and eigenfunctions; feature extraction; image classification; image retrieval; mammography; medical image processing; principal component analysis; support vector machines; 2D principal component analysis; Gaussian kernel; breast cancer early detection; computer-aided diagnostics; content-based image retrieval; eigenvalues; feature extraction; lesion classification; screening mammography; support vector machine; tissue classification; Breast; Cancer; Databases; Feature extraction; Lesions; Principal component analysis; Support vector machines; Breast density; Breast lesion; Computer-aided diagnosis; Content-based image retrieval; Mammography; Principal component analysis; Support vector machine;
fLanguage
English
Publisher
ieee
Conference_Titel
Graphics, Patterns and Images (Sibgrapi), 2011 24th SIBGRAPI Conference on
Conference_Location
Maceio, Alagoas
Print_ISBN
978-1-4577-1674-4
Type
conf
DOI
10.1109/SIBGRAPI.2011.40
Filename
6134754
Link To Document